From 9c7e6d69079e515da0091197dc07312838de037f Mon Sep 17 00:00:00 2001 From: nateraw Date: Fri, 2 Dec 2022 01:02:58 -0500 Subject: [PATCH 01/35] :art: structure docs --- hfdocs/README.md | 14 ++++++++++++ hfdocs/source/_toctree.yml | 29 +++++++++++++++++++++--- hfdocs/source/hf_hub.mdx | 3 +++ hfdocs/source/index.mdx | 4 ++++ hfdocs/source/inference.mdx | 3 +++ hfdocs/source/installation.mdx | 3 +++ hfdocs/source/quickstart.mdx | 3 +++ hfdocs/source/reference/augmentation.mdx | 3 +++ hfdocs/source/reference/data.mdx | 3 +++ hfdocs/source/reference/models.mdx | 3 +++ hfdocs/source/reference/optimization.mdx | 3 +++ hfdocs/source/training_script.mdx | 3 +++ 12 files changed, 71 insertions(+), 3 deletions(-) create mode 100644 hfdocs/README.md create mode 100644 hfdocs/source/hf_hub.mdx create mode 100644 hfdocs/source/inference.mdx create mode 100644 hfdocs/source/installation.mdx create mode 100644 hfdocs/source/quickstart.mdx create mode 100644 hfdocs/source/reference/augmentation.mdx create mode 100644 hfdocs/source/reference/data.mdx create mode 100644 hfdocs/source/reference/models.mdx create mode 100644 hfdocs/source/reference/optimization.mdx create mode 100644 hfdocs/source/training_script.mdx diff --git a/hfdocs/README.md b/hfdocs/README.md new file mode 100644 index 0000000000..f8819c4931 --- /dev/null +++ b/hfdocs/README.md @@ -0,0 +1,14 @@ +# Hugging Face Timm Docs + +## Getting Started + +``` +pip install git+https://github.com/huggingface/doc-builder.git@main#egg=hf-doc-builder +pip install watchdog black +``` + +## Preview the Docs Locally + +``` +doc-builder preview pytorch-image-models hfdocs/source --not_python_module +``` diff --git a/hfdocs/source/_toctree.yml b/hfdocs/source/_toctree.yml index 3fa994b688..2d4860589a 100644 --- a/hfdocs/source/_toctree.yml +++ b/hfdocs/source/_toctree.yml @@ -1,6 +1,30 @@ - sections: - local: index - title: Pytorch Image Models (timm) + title: Home + - local: quickstart + title: Quickstart + - local: installation + title: Installation + title: Get started +- sections: + - local: inference + title: Using Pretrained Models for Inference + - local: training_script + title: Training With The Official Training Script + - local: hf_hub + title: Share and Load Models from the Hugging Face Hub + title: Tutorials +- sections: + - local: reference/models + title: Models + - local: reference/augmentation + title: Augmentation + - local: reference/data + title: Data + - local: reference/optimization + title: Optimization + title: Reference +- sections: - local: models title: Model Summaries - local: results @@ -145,5 +169,4 @@ title: Wide ResNet - local: models/xception title: Xception - title: Get started - + title: Legacy Docs diff --git a/hfdocs/source/hf_hub.mdx b/hfdocs/source/hf_hub.mdx new file mode 100644 index 0000000000..e4f168b9d0 --- /dev/null +++ b/hfdocs/source/hf_hub.mdx @@ -0,0 +1,3 @@ +# Sharing and Loading Models From the Hugging Face Hub + +TODO \ No newline at end of file diff --git a/hfdocs/source/index.mdx b/hfdocs/source/index.mdx index 3733ae1ef9..58ec426165 100644 --- a/hfdocs/source/index.mdx +++ b/hfdocs/source/index.mdx @@ -2,6 +2,10 @@ ## Welcome +`timm` is a library containing SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations, and training/evaluation scripts. + +TODO - clean up, move code snippets to quickstart + Welcome to the `timm` documentation, a lean set of docs that covers the basics of `timm`. For a more comprehensive set of docs (currently under development), please visit [timmdocs](http://timm.fast.ai) by [Aman Arora](https://github.com/amaarora). diff --git a/hfdocs/source/inference.mdx b/hfdocs/source/inference.mdx new file mode 100644 index 0000000000..a31c31d53c --- /dev/null +++ b/hfdocs/source/inference.mdx @@ -0,0 +1,3 @@ +# Inference + +TODO \ No newline at end of file diff --git a/hfdocs/source/installation.mdx b/hfdocs/source/installation.mdx new file mode 100644 index 0000000000..2ae5251829 --- /dev/null +++ b/hfdocs/source/installation.mdx @@ -0,0 +1,3 @@ +# Installation + +TODO \ No newline at end of file diff --git a/hfdocs/source/quickstart.mdx b/hfdocs/source/quickstart.mdx new file mode 100644 index 0000000000..e3aa86a207 --- /dev/null +++ b/hfdocs/source/quickstart.mdx @@ -0,0 +1,3 @@ +# Quickstart + +TODO \ No newline at end of file diff --git a/hfdocs/source/reference/augmentation.mdx b/hfdocs/source/reference/augmentation.mdx new file mode 100644 index 0000000000..f9133aedf0 --- /dev/null +++ b/hfdocs/source/reference/augmentation.mdx @@ -0,0 +1,3 @@ +# Augmentations + +TODO \ No newline at end of file diff --git a/hfdocs/source/reference/data.mdx b/hfdocs/source/reference/data.mdx new file mode 100644 index 0000000000..1d4f4310ba --- /dev/null +++ b/hfdocs/source/reference/data.mdx @@ -0,0 +1,3 @@ +# Data + +TODO \ No newline at end of file diff --git a/hfdocs/source/reference/models.mdx b/hfdocs/source/reference/models.mdx new file mode 100644 index 0000000000..80ae058aa0 --- /dev/null +++ b/hfdocs/source/reference/models.mdx @@ -0,0 +1,3 @@ +# Models + +TODO \ No newline at end of file diff --git a/hfdocs/source/reference/optimization.mdx b/hfdocs/source/reference/optimization.mdx new file mode 100644 index 0000000000..f4b651c29a --- /dev/null +++ b/hfdocs/source/reference/optimization.mdx @@ -0,0 +1,3 @@ +# Optimization + +TODO \ No newline at end of file diff --git a/hfdocs/source/training_script.mdx b/hfdocs/source/training_script.mdx new file mode 100644 index 0000000000..66cce8acdc --- /dev/null +++ b/hfdocs/source/training_script.mdx @@ -0,0 +1,3 @@ +# Training Using the Official Training Script + +TODO \ No newline at end of file From c0f8e53468dfa7d8d231d8235c62742ea2871acc Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 15:42:18 -0500 Subject: [PATCH 02/35] :construction: wip docs --- hfdocs/source/index.mdx | 93 +++--------------------------------- hfdocs/source/quickstart.mdx | 48 ++++++++++++++++++- 2 files changed, 53 insertions(+), 88 deletions(-) diff --git a/hfdocs/source/index.mdx b/hfdocs/source/index.mdx index 58ec426165..259170b54f 100644 --- a/hfdocs/source/index.mdx +++ b/hfdocs/source/index.mdx @@ -2,92 +2,11 @@ ## Welcome -`timm` is a library containing SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations, and training/evaluation scripts. +`timm` is a library containing SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations, and training/evaluation scripts. It provides high-level APIs for popular model architectures and standard datasets, as well as utilities for low-level model manipulation. -TODO - clean up, move code snippets to quickstart +```python +import timm -Welcome to the `timm` documentation, a lean set of docs that covers the basics of `timm`. - -For a more comprehensive set of docs (currently under development), please visit [timmdocs](http://timm.fast.ai) by [Aman Arora](https://github.com/amaarora). - -## Install - -The library can be installed with pip: - -``` -pip install timm -``` - -I update the PyPi (pip) packages when I'm confident there are no significant model regressions from previous releases. If you want to pip install the bleeding edge from GitHub, use: -``` -pip install git+https://github.com/rwightman/pytorch-image-models.git -``` - -### Conda Environment - - - -- All development and testing has been done in Conda Python 3 environments on Linux x86-64 systems, specifically 3.7, 3.8, 3.9, 3.10 - -- Little to no care has been taken to be Python 2.x friendly and will not support it. If you run into any challenges running on Windows, or other OS, I'm definitely open to looking into those issues so long as it's in a reproducible (read Conda) environment. - -- PyTorch versions 1.9, 1.10, 1.11 have been tested with the latest versions of this code. - - - -I've tried to keep the dependencies minimal, the setup is as per the PyTorch default install instructions for Conda: - -```bash -conda create -n torch-env -conda activate torch-env -conda install pytorch torchvision cudatoolkit=11.3 -c pytorch -conda install pyyaml -``` - -## Load a Pretrained Model - -Pretrained models can be loaded using `timm.create_model` - -```py ->>> import timm - ->>> m = timm.create_model('mobilenetv3_large_100', pretrained=True) ->>> m.eval() -``` - -## List Models with Pretrained Weights - -```py ->>> import timm ->>> from pprint import pprint ->>> model_names = timm.list_models(pretrained=True) ->>> pprint(model_names) -[ - 'adv_inception_v3', - 'cspdarknet53', - 'cspresnext50', - 'densenet121', - 'densenet161', - 'densenet169', - 'densenet201', - 'densenetblur121d', - 'dla34', - 'dla46_c', -] -``` - -## List Model Architectures by Wildcard - -```py ->>> import timm ->>> from pprint import pprint ->>> model_names = timm.list_models('*resne*t*') ->>> pprint(model_names) -[ - 'cspresnet50', - 'cspresnet50d', - 'cspresnet50w', - 'cspresnext50', - ... -] -``` +# Load a Pretrained Model +model = timm.create_model('resnet18', pretrained=True) +``` \ No newline at end of file diff --git a/hfdocs/source/quickstart.mdx b/hfdocs/source/quickstart.mdx index e3aa86a207..31614fcb71 100644 --- a/hfdocs/source/quickstart.mdx +++ b/hfdocs/source/quickstart.mdx @@ -1,3 +1,49 @@ # Quickstart -TODO \ No newline at end of file +## Load a Pretrained Model + +Pretrained models can be loaded using `timm.create_model` + +```py +>>> import timm + +>>> m = timm.create_model('mobilenetv3_large_100', pretrained=True) +>>> m.eval() +``` + +## List Models with Pretrained Weights + +```py +>>> import timm +>>> from pprint import pprint +>>> model_names = timm.list_models(pretrained=True) +>>> pprint(model_names) +[ + 'adv_inception_v3', + 'cspdarknet53', + 'cspresnext50', + 'densenet121', + 'densenet161', + 'densenet169', + 'densenet201', + 'densenetblur121d', + 'dla34', + 'dla46_c', +] +``` + +## List Model Architectures by Wildcard + +```py +>>> import timm +>>> from pprint import pprint +>>> model_names = timm.list_models('*resne*t*') +>>> pprint(model_names) +[ + 'cspresnet50', + 'cspresnet50d', + 'cspresnet50w', + 'cspresnext50', + ... +] +``` From ffae459814bca853d204d4735b24373ddbedc39f Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 15:53:15 -0500 Subject: [PATCH 03/35] :memo: add installation doc --- hfdocs/source/index.mdx | 4 +- hfdocs/source/installation.mdx | 74 +++++++++++++++++++++++++++++++++- 2 files changed, 74 insertions(+), 4 deletions(-) diff --git a/hfdocs/source/index.mdx b/hfdocs/source/index.mdx index 259170b54f..fb7634b23e 100644 --- a/hfdocs/source/index.mdx +++ b/hfdocs/source/index.mdx @@ -1,6 +1,4 @@ -# Getting Started - -## Welcome +# timm `timm` is a library containing SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations, and training/evaluation scripts. It provides high-level APIs for popular model architectures and standard datasets, as well as utilities for low-level model manipulation. diff --git a/hfdocs/source/installation.mdx b/hfdocs/source/installation.mdx index 2ae5251829..1be87857c9 100644 --- a/hfdocs/source/installation.mdx +++ b/hfdocs/source/installation.mdx @@ -1,3 +1,75 @@ # Installation -TODO \ No newline at end of file +Before you start, you'll need to setup your environment and install the appropriate packages. `timm` is tested on **Python 3+**. + +## Virtual Environment + +You should install `timm` in a [virtual environment](https://docs.python.org/3/library/venv.html) to keep things tidy and avoid dependency conflicts. + +1. Create and navigate to your project directory: + + ```bash + mkdir ~/my-project + cd ~/my-project + ``` + +2. Start a virtual environment inside your directory: + + ```bash + python -m venv .env + ``` + +3. Activate and deactivate the virtual environment with the following commands: + + ```bash + # Activate the virtual environment + source .env/bin/activate + + # Deactivate the virtual environment + source .env/bin/deactivate + ``` +` +Once you've created your virtual environment, you can install `timm` in it. + +## Using pip + +The most straightforward way to install `timm` is with pip: + +```bash +pip install timm +``` + +Alternatively, you can install `timm` from GitHub directly to get the latest, bleeding-edge version: + +```bash +pip install git+https://github.com/rwightman/pytorch-image-models.git +``` + +```bash +Run the following command to check if `timm` has been properly installed: + +```bash +python -c "from timm import list_models; print(list_models(pretrained=True)[:5])" +``` + +This command lists the first five pretrained models available in `timm` (which are sorted alphebetically). You should see the following output: + +```python +['adv_inception_v3', 'bat_resnext26ts', 'beit_base_patch16_224', 'beit_base_patch16_224_in22k', 'beit_base_patch16_384'] +``` + +## From Source + +Building `timm` from source lets you make changes to the code base. To install from the source, clone the repository and install with the following commands: + +```bash +git clone https://github.com/rwightman/timm.git +cd timm +pip install -e . +``` + +Again, you can check if `timm` was properly installed with the following command: + +```bash +python -c "from timm import list_models; print(list_models(pretrained=True)[:5])" +``` From 74897ad3333d8e1a94bcf8aa6dc26626ca1085fd Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 16:11:02 -0500 Subject: [PATCH 04/35] :memo: wip docs --- hfdocs/source/installation.mdx | 1 - 1 file changed, 1 deletion(-) diff --git a/hfdocs/source/installation.mdx b/hfdocs/source/installation.mdx index 1be87857c9..a83a61040e 100644 --- a/hfdocs/source/installation.mdx +++ b/hfdocs/source/installation.mdx @@ -45,7 +45,6 @@ Alternatively, you can install `timm` from GitHub directly to get the latest, bl pip install git+https://github.com/rwightman/pytorch-image-models.git ``` -```bash Run the following command to check if `timm` has been properly installed: ```bash From 9c2c5bfaaa4f9718d3e9a17b9df312ed680da9b9 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 16:15:35 -0500 Subject: [PATCH 05/35] :memo: wip docs --- hfdocs/source/index.mdx | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/hfdocs/source/index.mdx b/hfdocs/source/index.mdx index fb7634b23e..0a9f08a19e 100644 --- a/hfdocs/source/index.mdx +++ b/hfdocs/source/index.mdx @@ -1,10 +1,7 @@ # timm -`timm` is a library containing SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations, and training/evaluation scripts. It provides high-level APIs for popular model architectures and standard datasets, as well as utilities for low-level model manipulation. +`timm` is a library containing SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations, and training/evaluation scripts. -```python -import timm +It comes packaged with >100 pretrained models, and is designed to be flexible and easy to use. -# Load a Pretrained Model -model = timm.create_model('resnet18', pretrained=True) -``` \ No newline at end of file +Read the [quick start guide](quickstart) to get up and running with the `timm` library. You will learn how to load, discover, and use pretrained models included in the library. From ecaa5d9c9fe3c78638e06bb0916f4bc26e738211 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 16:34:08 -0500 Subject: [PATCH 06/35] :memo: wip docs --- hfdocs/source/_toctree.yml | 50 +++++++++++++++++++----------------- hfdocs/source/quickstart.mdx | 38 ++++++++++++++++++++++++++- 2 files changed, 63 insertions(+), 25 deletions(-) diff --git a/hfdocs/source/_toctree.yml b/hfdocs/source/_toctree.yml index 2d4860589a..5f1a2ce10b 100644 --- a/hfdocs/source/_toctree.yml +++ b/hfdocs/source/_toctree.yml @@ -9,36 +9,14 @@ - sections: - local: inference title: Using Pretrained Models for Inference + - local: feature_extraction + title: Using Pretrained Models as Feature Extractors - local: training_script title: Training With The Official Training Script - local: hf_hub title: Share and Load Models from the Hugging Face Hub title: Tutorials - sections: - - local: reference/models - title: Models - - local: reference/augmentation - title: Augmentation - - local: reference/data - title: Data - - local: reference/optimization - title: Optimization - title: Reference -- sections: - - local: models - title: Model Summaries - - local: results - title: Results - - local: scripts - title: Scripts - - local: training_hparam_examples - title: Training Examples - - local: feature_extraction - title: Feature Extraction - - local: changes - title: Recent Changes - - local: archived_changes - title: Archived Changes - local: model_pages title: Model Pages isExpanded: false @@ -169,4 +147,28 @@ title: Wide ResNet - local: models/xception title: Xception + title: Available Models +- sections: + - local: reference/models + title: Models + - local: reference/augmentation + title: Augmentation + - local: reference/data + title: Data + - local: reference/optimization + title: Optimization + title: Reference +- sections: + - local: models + title: Model Summaries + - local: results + title: Results + - local: scripts + title: Scripts + - local: training_hparam_examples + title: Training Examples + - local: changes + title: Recent Changes + - local: archived_changes + title: Archived Changes title: Legacy Docs diff --git a/hfdocs/source/quickstart.mdx b/hfdocs/source/quickstart.mdx index 31614fcb71..9d87886841 100644 --- a/hfdocs/source/quickstart.mdx +++ b/hfdocs/source/quickstart.mdx @@ -1,5 +1,13 @@ # Quickstart +This quickstart is intended for developers who are ready to dive into the code and see an example of how to integrate `timm` into their model training workflow. + +First, you'll need to install `timm`. For more information on installation, see [Installation](installation). + +```bash +pip install timm +``` + ## Load a Pretrained Model Pretrained models can be loaded using `timm.create_model` @@ -11,8 +19,36 @@ Pretrained models can be loaded using `timm.create_model` >>> m.eval() ``` +## Fine-Tune a Pretrained Model + +You can finetune any of the pre-trained models just by changing the classifier (the last layer). + +```py +>>> model = timm.create_model('mobilenetv3_large_100', pretrained=True, num_classes=NUM_FINETUNE_CLASSES) +``` + +To fine-tune on your own dataset, you have to write a PyTorch training loop or adapt `timm`'s [training script](training_script) to use your dataset. + +## Use a Pretrained Model for Feature Extraction + +Without modifying the network, one can call model.forward_features(input) on any model instead of the usual model(input). This will bypass the head classifier and global pooling for networks. + +For a more in depth guide to using `timm` for feature extraction, see [Feature Extraction](feature_extraction). + +```py +>>> import timm +>>> import torch +>>> x = torch.randn(1, 3, 224, 224) +>>> model = timm.create_model('mobilenetv3_large_100', pretrained=True) +>>> features = model.forward_features(x) +>>> print(features.shape) +torch.Size([1, 960, 7, 7]) +``` + ## List Models with Pretrained Weights +You can list all models with pretrained weights using `timm.list_models`. + ```py >>> import timm >>> from pprint import pprint @@ -32,7 +68,7 @@ Pretrained models can be loaded using `timm.create_model` ] ``` -## List Model Architectures by Wildcard +You can also list models with a specific pattern in their name. ```py >>> import timm From e5b16e2e39f7edfd94ee6c3c3eef07248c4015dd Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 16:56:12 -0500 Subject: [PATCH 07/35] :memo: wip docs --- hfdocs/source/_toctree.yml | 2 +- hfdocs/source/quickstart.mdx | 197 ++++++++++++++++++++++++++++++----- 2 files changed, 171 insertions(+), 28 deletions(-) diff --git a/hfdocs/source/_toctree.yml b/hfdocs/source/_toctree.yml index 5f1a2ce10b..ab0a3c3015 100644 --- a/hfdocs/source/_toctree.yml +++ b/hfdocs/source/_toctree.yml @@ -147,7 +147,7 @@ title: Wide ResNet - local: models/xception title: Xception - title: Available Models + title: Model Pages - sections: - local: reference/models title: Models diff --git a/hfdocs/source/quickstart.mdx b/hfdocs/source/quickstart.mdx index 9d87886841..fc52ae4b2d 100644 --- a/hfdocs/source/quickstart.mdx +++ b/hfdocs/source/quickstart.mdx @@ -10,7 +10,9 @@ pip install timm ## Load a Pretrained Model -Pretrained models can be loaded using `timm.create_model` +Pretrained models can be loaded using `timm.create_model`. + +Here, we load the pretrained `mobilenetv3_large_100` model. ```py >>> import timm @@ -19,35 +21,13 @@ Pretrained models can be loaded using `timm.create_model` >>> m.eval() ``` -## Fine-Tune a Pretrained Model - -You can finetune any of the pre-trained models just by changing the classifier (the last layer). - -```py ->>> model = timm.create_model('mobilenetv3_large_100', pretrained=True, num_classes=NUM_FINETUNE_CLASSES) -``` - -To fine-tune on your own dataset, you have to write a PyTorch training loop or adapt `timm`'s [training script](training_script) to use your dataset. - -## Use a Pretrained Model for Feature Extraction - -Without modifying the network, one can call model.forward_features(input) on any model instead of the usual model(input). This will bypass the head classifier and global pooling for networks. - -For a more in depth guide to using `timm` for feature extraction, see [Feature Extraction](feature_extraction). - -```py ->>> import timm ->>> import torch ->>> x = torch.randn(1, 3, 224, 224) ->>> model = timm.create_model('mobilenetv3_large_100', pretrained=True) ->>> features = model.forward_features(x) ->>> print(features.shape) -torch.Size([1, 960, 7, 7]) -``` + +**Note:** The returned PyTorch model is set to `train` mode by default, so you must call `.eval()` on it if you plan to use it for inference. + ## List Models with Pretrained Weights -You can list all models with pretrained weights using `timm.list_models`. +To list models packaged with `timm`, you can use `timm.list_models`. If you specify `pretrained=True`, this function will only return model names that have associated pretrained weights available. ```py >>> import timm @@ -83,3 +63,166 @@ You can also list models with a specific pattern in their name. ... ] ``` + +## Fine-Tune a Pretrained Model + +You can finetune any of the pre-trained models just by changing the classifier (the last layer). + +```py +>>> model = timm.create_model('mobilenetv3_large_100', pretrained=True, num_classes=NUM_FINETUNE_CLASSES) +``` + +To fine-tune on your own dataset, you have to write a PyTorch training loop or adapt `timm`'s [training script](training_script) to use your dataset. + +## Use a Pretrained Model for Feature Extraction + +Without modifying the network, one can call model.forward_features(input) on any model instead of the usual model(input). This will bypass the head classifier and global pooling for networks. + +For a more in depth guide to using `timm` for feature extraction, see [Feature Extraction](feature_extraction). + +```py +>>> import timm +>>> import torch +>>> x = torch.randn(1, 3, 224, 224) +>>> model = timm.create_model('mobilenetv3_large_100', pretrained=True) +>>> features = model.forward_features(x) +>>> print(features.shape) +torch.Size([1, 960, 7, 7]) +``` + +## Image Augmentation + +To transform images into valid inputs for a model, you can use `timm.data.create_transform`, providing the desired `input_size` that the model expects. + +This will return a generic transform that uses reasonable defaults. + +```py +>>> timm.data.create_transform((3, 224, 224)) +Compose( + Resize(size=256, interpolation=bilinear, max_size=None, antialias=None) + CenterCrop(size=(224, 224)) + ToTensor() + Normalize(mean=tensor([0.4850, 0.4560, 0.4060]), std=tensor([0.2290, 0.2240, 0.2250])) +) +``` + +Pretrained models have specific transforms that were applied to images fed into them while training. If you use the wrong transform on your image, the model won't understand what it's seeing! + +To figure out which transformations were used for a given pretrained model, we can start by taking a look at its `pretrained_cfg` + +```py +>>> model.pretrained_cfg +{'url': 'https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/mobilenetv3_large_100_ra-f55367f5.pth', + 'num_classes': 1000, + 'input_size': (3, 224, 224), + 'pool_size': (7, 7), + 'crop_pct': 0.875, + 'interpolation': 'bicubic', + 'mean': (0.485, 0.456, 0.406), + 'std': (0.229, 0.224, 0.225), + 'first_conv': 'conv_stem', + 'classifier': 'classifier', + 'architecture': 'mobilenetv3_large_100'} +``` + +We can then resolve only the data related configuration by using `timm.data.resolve_data_config`. + +```py +>>> timm.data.resolve_data_config(model.pretrained_cfg) +{'input_size': (3, 224, 224), + 'interpolation': 'bicubic', + 'mean': (0.485, 0.456, 0.406), + 'std': (0.229, 0.224, 0.225), + 'crop_pct': 0.875} +``` + +We can pass this data config to timm.data.create_transform to initialize the model's associated transform. + +```py +>>> data_cfg = timm.data.resolve_data_config(model.pretrained_cfg) +>>> transform = timm.data.create_transform(**data_cfg) +>>> transform +Compose( + Resize(size=256, interpolation=bicubic, max_size=None, antialias=None) + CenterCrop(size=(224, 224)) + ToTensor() + Normalize(mean=tensor([0.4850, 0.4560, 0.4060]), std=tensor([0.2290, 0.2240, 0.2250])) +) +``` + + + Note: Here, the pretrained model's config happens to be the same as the generic config we made earlier. This is not always the case. So, it's safer to use the data config to create the transform as we did here instead of using the generic transform. + + +## Using Pretrained Models for Inference + +Here, we will put together the above sections and use a pretrained model for inference. + +First we'll need an image to do inference on. Here we load a picture of a leaf from the web: + +```py +>>> import requests +>>> from PIL import Image +>>> from io import BytesIO +>>> url = 'https://datasets-server.huggingface.co/assets/imagenet-1k/--/default/test/12/image/image.jpg' +>>> image = Image.open(requests.get(url, stream=True).raw) +>>> image +``` + +Here's the image we loaded: + +An Image from a link + +Now, we'll create our model and transforms again. This time, we make sure to set our model in evaluation mode. + +```py +>>> model = timm.create_model('mobilenetv3_large_100', pretrained=True).eval() +>>> transform = timm.data.create_transform( + **timm.data.resolve_data_config(model.pretrained_cfg) +) +``` + +We can prepare this image for the model by passing it to the transform. + +```py +>>> image_tensor = transform(image) +>>> image_tensor.shape +torch.Size([3, 224, 224]) +``` + +Now we can pass that image to the model to get the predictions. We use `unsqueeze(0)` in this case, as the model is expecting a batch dimension. + +```py +>>> output = model(image_tensor.unsqueeze(0)) +>>> output.shape +torch.Size([1, 1000]) +``` + +To get the predicted probabilities, we apply softmax to the output. This leaves us with a tensor of shape `(num_classes,)`. + +```py +>>> probabilities = torch.nn.functional.softmax(output[0], dim=0) +>>> probabilities.shape +torch.Size([1000]) +``` + +Now we'll find the top 5 predicted class indexes and values using `torch.topk`. + +```py +>>> values, indices = torch.topk(probabilities, 5) +>>> indices +tensor([162, 166, 161, 164, 167]) +``` + +If we check the imagenet labels for the top index, we can see what the model predicted... + +```py +>>> IMAGENET_1k_URL = 'https://storage.googleapis.com/bit_models/ilsvrc2012_wordnet_lemmas.txt' +>>> IMAGENET_1k_LABELS = requests.get(IMAGENET_1k_URL).text.strip().split('\n') +>>> [{'label': IMAGENET_1k_LABELS[idx], 'value': val.item()} for val, idx in zip(values, indices)] +[{'label': 'beagle', 'value': 0.8486220836639404}, + {'label': 'Walker_hound, Walker_foxhound', 'value': 0.03753996267914772}, + {'label': 'basset, basset_hound', 'value': 0.024628572165966034}, + {'label': 'bluetick', 'value': 0.010317106731235981}, + {'label': 'English_foxhound', 'value': 0.006958036217838526}] +``` From 101a7ced95c32b4b07c0b1a1f93c702c11406fed Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 17:00:11 -0500 Subject: [PATCH 08/35] :memo: wip docs --- hfdocs/source/_toctree.yml | 257 +++++++++++++++++----------------- hfdocs/source/model_pages.mdx | 5 - 2 files changed, 127 insertions(+), 135 deletions(-) delete mode 100644 hfdocs/source/model_pages.mdx diff --git a/hfdocs/source/_toctree.yml b/hfdocs/source/_toctree.yml index ab0a3c3015..3ac7f9f9e1 100644 --- a/hfdocs/source/_toctree.yml +++ b/hfdocs/source/_toctree.yml @@ -17,137 +17,134 @@ title: Share and Load Models from the Hugging Face Hub title: Tutorials - sections: - - local: model_pages - title: Model Pages - isExpanded: false - sections: - - local: models/adversarial-inception-v3 - title: Adversarial Inception v3 - - local: models/advprop - title: AdvProp (EfficientNet) - - local: models/big-transfer - title: Big Transfer (BiT) - - local: models/csp-darknet - title: CSP-DarkNet - - local: models/csp-resnet - title: CSP-ResNet - - local: models/csp-resnext - title: CSP-ResNeXt - - local: models/densenet - title: DenseNet - - local: models/dla - title: Deep Layer Aggregation - - local: models/dpn - title: Dual Path Network (DPN) - - local: models/ecaresnet - title: ECA-ResNet - - local: models/efficientnet - title: EfficientNet - - local: models/efficientnet-pruned - title: EfficientNet (Knapsack Pruned) - - local: models/ensemble-adversarial - title: Ensemble Adversarial Inception ResNet v2 - - local: models/ese-vovnet - title: ESE-VoVNet - - local: models/fbnet - title: FBNet - - local: models/gloun-inception-v3 - title: (Gluon) Inception v3 - - local: models/gloun-resnet - title: (Gluon) ResNet - - local: models/gloun-resnext - title: (Gluon) ResNeXt - - local: models/gloun-senet - title: (Gluon) SENet - - local: models/gloun-seresnext - title: (Gluon) SE-ResNeXt - - local: models/gloun-xception - title: (Gluon) Xception - - local: models/hrnet - title: HRNet - - local: models/ig-resnext - title: Instagram ResNeXt WSL - - local: models/inception-resnet-v2 - title: Inception ResNet v2 - - local: models/inception-v3 - title: Inception v3 - - local: models/inception-v4 - title: Inception v4 - - local: models/legacy-se-resnet - title: (Legacy) SE-ResNet - - local: models/legacy-se-resnext - title: (Legacy) SE-ResNeXt - - local: models/legacy-senet - title: (Legacy) SENet - - local: models/mixnet - title: MixNet - - local: models/mnasnet - title: MnasNet - - local: models/mobilenet-v2 - title: MobileNet v2 - - local: models/mobilenet-v3 - title: MobileNet v3 - - local: models/nasnet - title: NASNet - - local: models/noisy-student - title: Noisy Student (EfficientNet) - - local: models/pnasnet - title: PNASNet - - local: models/regnetx - title: RegNetX - - local: models/regnety - title: RegNetY - - local: models/res2net - title: Res2Net - - local: models/res2next - title: Res2NeXt - - local: models/resnest - title: ResNeSt - - local: models/resnet - title: ResNet - - local: models/resnet-d - title: ResNet-D - - local: models/resnext - title: ResNeXt - - local: models/rexnet - title: RexNet - - local: models/se-resnet - title: SE-ResNet - - local: models/selecsls - title: SelecSLS - - local: models/seresnext - title: SE-ResNeXt - - local: models/skresnet - title: SK-ResNet - - local: models/skresnext - title: SK-ResNeXt - - local: models/spnasnet - title: SPNASNet - - local: models/ssl-resnet - title: SSL ResNet - - local: models/swsl-resnet - title: SWSL ResNet - - local: models/swsl-resnext - title: SWSL ResNeXt - - local: models/tf-efficientnet - title: (Tensorflow) EfficientNet - - local: models/tf-efficientnet-condconv - title: (Tensorflow) EfficientNet CondConv - - local: models/tf-efficientnet-lite - title: (Tensorflow) EfficientNet Lite - - local: models/tf-inception-v3 - title: (Tensorflow) Inception v3 - - local: models/tf-mixnet - title: (Tensorflow) MixNet - - local: models/tf-mobilenet-v3 - title: (Tensorflow) MobileNet v3 - - local: models/tresnet - title: TResNet - - local: models/wide-resnet - title: Wide ResNet - - local: models/xception - title: Xception + - local: models/adversarial-inception-v3 + title: Adversarial Inception v3 + - local: models/advprop + title: AdvProp (EfficientNet) + - local: models/big-transfer + title: Big Transfer (BiT) + - local: models/csp-darknet + title: CSP-DarkNet + - local: models/csp-resnet + title: CSP-ResNet + - local: models/csp-resnext + title: CSP-ResNeXt + - local: models/densenet + title: DenseNet + - local: models/dla + title: Deep Layer Aggregation + - local: models/dpn + title: Dual Path Network (DPN) + - local: models/ecaresnet + title: ECA-ResNet + - local: models/efficientnet + title: EfficientNet + - local: models/efficientnet-pruned + title: EfficientNet (Knapsack Pruned) + - local: models/ensemble-adversarial + title: Ensemble Adversarial Inception ResNet v2 + - local: models/ese-vovnet + title: ESE-VoVNet + - local: models/fbnet + title: FBNet + - local: models/gloun-inception-v3 + title: (Gluon) Inception v3 + - local: models/gloun-resnet + title: (Gluon) ResNet + - local: models/gloun-resnext + title: (Gluon) ResNeXt + - local: models/gloun-senet + title: (Gluon) SENet + - local: models/gloun-seresnext + title: (Gluon) SE-ResNeXt + - local: models/gloun-xception + title: (Gluon) Xception + - local: models/hrnet + title: HRNet + - local: models/ig-resnext + title: Instagram ResNeXt WSL + - local: models/inception-resnet-v2 + title: Inception ResNet v2 + - local: models/inception-v3 + title: Inception v3 + - local: models/inception-v4 + title: Inception v4 + - local: models/legacy-se-resnet + title: (Legacy) SE-ResNet + - local: models/legacy-se-resnext + title: (Legacy) SE-ResNeXt + - local: models/legacy-senet + title: (Legacy) SENet + - local: models/mixnet + title: MixNet + - local: models/mnasnet + title: MnasNet + - local: models/mobilenet-v2 + title: MobileNet v2 + - local: models/mobilenet-v3 + title: MobileNet v3 + - local: models/nasnet + title: NASNet + - local: models/noisy-student + title: Noisy Student (EfficientNet) + - local: models/pnasnet + title: PNASNet + - local: models/regnetx + title: RegNetX + - local: models/regnety + title: RegNetY + - local: models/res2net + title: Res2Net + - local: models/res2next + title: Res2NeXt + - local: models/resnest + title: ResNeSt + - local: models/resnet + title: ResNet + - local: models/resnet-d + title: ResNet-D + - local: models/resnext + title: ResNeXt + - local: models/rexnet + title: RexNet + - local: models/se-resnet + title: SE-ResNet + - local: models/selecsls + title: SelecSLS + - local: models/seresnext + title: SE-ResNeXt + - local: models/skresnet + title: SK-ResNet + - local: models/skresnext + title: SK-ResNeXt + - local: models/spnasnet + title: SPNASNet + - local: models/ssl-resnet + title: SSL ResNet + - local: models/swsl-resnet + title: SWSL ResNet + - local: models/swsl-resnext + title: SWSL ResNeXt + - local: models/tf-efficientnet + title: (Tensorflow) EfficientNet + - local: models/tf-efficientnet-condconv + title: (Tensorflow) EfficientNet CondConv + - local: models/tf-efficientnet-lite + title: (Tensorflow) EfficientNet Lite + - local: models/tf-inception-v3 + title: (Tensorflow) Inception v3 + - local: models/tf-mixnet + title: (Tensorflow) MixNet + - local: models/tf-mobilenet-v3 + title: (Tensorflow) MobileNet v3 + - local: models/tresnet + title: TResNet + - local: models/wide-resnet + title: Wide ResNet + - local: models/xception + title: Xception title: Model Pages + isExpanded: false - sections: - local: reference/models title: Models diff --git a/hfdocs/source/model_pages.mdx b/hfdocs/source/model_pages.mdx deleted file mode 100644 index a78663f13f..0000000000 --- a/hfdocs/source/model_pages.mdx +++ /dev/null @@ -1,5 +0,0 @@ -# Available Models - -`timm` comes bundled with a number of model architectures and corresponding pretrained models. - -In these pages, you will find the models available in the `timm` library, as well as information on how to use them. \ No newline at end of file From d0a067705f550b3637264837da42a3d399693416 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 17:19:11 -0500 Subject: [PATCH 09/35] :memo: add basic reference docs --- hfdocs/source/reference/augmentation.mdx | 3 --- hfdocs/source/reference/data.mdx | 6 +++++- hfdocs/source/reference/models.mdx | 4 +++- hfdocs/source/reference/optimization.mdx | 11 ++++++++++- 4 files changed, 18 insertions(+), 6 deletions(-) delete mode 100644 hfdocs/source/reference/augmentation.mdx diff --git a/hfdocs/source/reference/augmentation.mdx b/hfdocs/source/reference/augmentation.mdx deleted file mode 100644 index f9133aedf0..0000000000 --- a/hfdocs/source/reference/augmentation.mdx +++ /dev/null @@ -1,3 +0,0 @@ -# Augmentations - -TODO \ No newline at end of file diff --git a/hfdocs/source/reference/data.mdx b/hfdocs/source/reference/data.mdx index 1d4f4310ba..bf63503768 100644 --- a/hfdocs/source/reference/data.mdx +++ b/hfdocs/source/reference/data.mdx @@ -1,3 +1,7 @@ # Data -TODO \ No newline at end of file +[[autodoc]] timm.data.create_dataset + +[[autodoc]] timm.data.create_loader + +[[autodoc]] timm.data.create_transform \ No newline at end of file diff --git a/hfdocs/source/reference/models.mdx b/hfdocs/source/reference/models.mdx index 80ae058aa0..31bb3c2713 100644 --- a/hfdocs/source/reference/models.mdx +++ b/hfdocs/source/reference/models.mdx @@ -1,3 +1,5 @@ # Models -TODO \ No newline at end of file +[[autodoc]] timm.create_model + +[[autodoc]] timm.list_models diff --git a/hfdocs/source/reference/optimization.mdx b/hfdocs/source/reference/optimization.mdx index f4b651c29a..6f6191140d 100644 --- a/hfdocs/source/reference/optimization.mdx +++ b/hfdocs/source/reference/optimization.mdx @@ -1,3 +1,12 @@ # Optimization -TODO \ No newline at end of file +## Optimizers + +[[autodoc]] timm.optim.optim_factory.create_optimizer + +## Schedulers + +[[autodoc]] timm.scheduler.cosine_lr.CosineLRScheduler +[[autodoc]] timm.scheduler.step_lr.StepLRScheduler +[[autodoc]] timm.scheduler.tanh_lr.TanhLRScheduler +[[autodoc]] timm.scheduler.plateau_lr.PlateauLRScheduler From 61b0e8296e2799074ec7278429e267f0c2238691 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 17:25:06 -0500 Subject: [PATCH 10/35] :memo: remove augmentation from toctree --- hfdocs/source/_toctree.yml | 2 -- 1 file changed, 2 deletions(-) diff --git a/hfdocs/source/_toctree.yml b/hfdocs/source/_toctree.yml index 3ac7f9f9e1..71fdcc6248 100644 --- a/hfdocs/source/_toctree.yml +++ b/hfdocs/source/_toctree.yml @@ -148,8 +148,6 @@ - sections: - local: reference/models title: Models - - local: reference/augmentation - title: Augmentation - local: reference/data title: Data - local: reference/optimization From d3f7bb4fb7e9666409edb59c06eef90ce45e0090 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 18:21:36 -0500 Subject: [PATCH 11/35] :construction_worker: update pr doc builder to bugfix branch --- .github/workflows/build_pr_documentation.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index 4b1b5c9dbf..934a7acdd4 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -9,7 +9,7 @@ concurrency: jobs: build: - uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main + uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@repo-owner-bugfix with: commit_sha: ${{ github.event.pull_request.head.sha }} pr_number: ${{ github.event.number }} From 84de7c2640999f1c84a30289150f6ec6ed24cd31 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 18:43:15 -0500 Subject: [PATCH 12/35] :memo: wip docs --- hfdocs/source/reference/optimization.mdx | 34 +++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) diff --git a/hfdocs/source/reference/optimization.mdx b/hfdocs/source/reference/optimization.mdx index 6f6191140d..82c21bf631 100644 --- a/hfdocs/source/reference/optimization.mdx +++ b/hfdocs/source/reference/optimization.mdx @@ -1,12 +1,44 @@ # Optimization +This page contains the API reference documentation for optimization-related tools (optimizers, learning rate schedulers, etc) included in `timm`. + ## Optimizers +### Factory functions + [[autodoc]] timm.optim.optim_factory.create_optimizer +[[autodoc]] timm.optim.optim_factory.create_optimizer_v2 + +### Optimizer Classes + +[[autodoc]] timm.optim.adabelief.AdaBelief +[[autodoc]] timm.optim.adafactor.Adafactor +[[autodoc]] timm.optim.adahessian.Adahessian +[[autodoc]] timm.optim.adamp.AdamP +[[autodoc]] timm.optim.adamw.AdamW +[[autodoc]] timm.optim.lamb.Lamb +[[autodoc]] timm.optim.lars.Lars +[[autodoc]] timm.optim.lookahead.Lookahead +[[autodoc]] timm.optim.madgrad.MADGRAD +[[autodoc]] timm.optim.nadam.Nadam +[[autodoc]] timm.optim.nvnovograd.NvNovoGrad +[[autodoc]] timm.optim.radam.RAdam +[[autodoc]] timm.optim.rmsprop_tf.RMSpropTF +[[autodoc]] timm.optim.sgdp.SGDP + ## Schedulers +### Factory functions + +[[autodoc]] timm.scheduler.scheduler_factory.create_scheduler +[[autodoc]] timm.scheduler.scheduler_factory.create_scheduler_v2 + +### Scheduler Classes + [[autodoc]] timm.scheduler.cosine_lr.CosineLRScheduler +[[autodoc]] timm.scheduler.multistep_lr.MultiStepLRScheduler +[[autodoc]] timm.scheduler.plateau_lr.PlateauLRScheduler +[[autodoc]] timm.scheduler.poly_lr.PolyLRScheduler [[autodoc]] timm.scheduler.step_lr.StepLRScheduler [[autodoc]] timm.scheduler.tanh_lr.TanhLRScheduler -[[autodoc]] timm.scheduler.plateau_lr.PlateauLRScheduler From 51a820676878dbe26260bb566ffc522e684ce8f6 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 18:52:23 -0500 Subject: [PATCH 13/35] :construction: wip --- hfdocs/source/quickstart.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hfdocs/source/quickstart.mdx b/hfdocs/source/quickstart.mdx index fc52ae4b2d..7c925101bd 100644 --- a/hfdocs/source/quickstart.mdx +++ b/hfdocs/source/quickstart.mdx @@ -225,4 +225,4 @@ If we check the imagenet labels for the top index, we can see what the model pre {'label': 'basset, basset_hound', 'value': 0.024628572165966034}, {'label': 'bluetick', 'value': 0.010317106731235981}, {'label': 'English_foxhound', 'value': 0.006958036217838526}] -``` +``` \ No newline at end of file From 06c6dc79afc1c7a9e9bd33467f010b3b286b3092 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 19:00:50 -0500 Subject: [PATCH 14/35] :construction_worker: bump CI --- hfdocs/source/reference/data.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hfdocs/source/reference/data.mdx b/hfdocs/source/reference/data.mdx index bf63503768..0b00c9e3f1 100644 --- a/hfdocs/source/reference/data.mdx +++ b/hfdocs/source/reference/data.mdx @@ -4,4 +4,4 @@ [[autodoc]] timm.data.create_loader -[[autodoc]] timm.data.create_transform \ No newline at end of file +[[autodoc]] timm.data.create_transform From c20708a77d3fd07a31f7f4a0a098311987dcce54 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 20:19:19 -0500 Subject: [PATCH 15/35] :construction: wip --- .github/workflows/build_pr_documentation.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index 934a7acdd4..fccc9609c1 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -17,3 +17,4 @@ jobs: package_name: timm repo_owner: rwightman path_to_docs: pytorch-image-models/hfdocs/source + version_tag_suffix: '' \ No newline at end of file From a973bb1619f804200885ecbfafa466f26ed2e9d3 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 20:31:23 -0500 Subject: [PATCH 16/35] :construction: bump CI --- .github/workflows/build_pr_documentation.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index fccc9609c1..0ea51e93d1 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -17,4 +17,4 @@ jobs: package_name: timm repo_owner: rwightman path_to_docs: pytorch-image-models/hfdocs/source - version_tag_suffix: '' \ No newline at end of file + version_tag_suffix: '' From daf3a1ac0d8f483f22d5443b972188ce8ce8c3d1 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 20:37:52 -0500 Subject: [PATCH 17/35] :construction: wip --- .github/workflows/build_pr_documentation.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index 0ea51e93d1..fccc9609c1 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -17,4 +17,4 @@ jobs: package_name: timm repo_owner: rwightman path_to_docs: pytorch-image-models/hfdocs/source - version_tag_suffix: '' + version_tag_suffix: '' \ No newline at end of file From dd780e08399e3d7daaddcded7bed3341d9d4af1c Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 20:49:10 -0500 Subject: [PATCH 18/35] :construction: wip --- .github/workflows/build_pr_documentation.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index fccc9609c1..0ea51e93d1 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -17,4 +17,4 @@ jobs: package_name: timm repo_owner: rwightman path_to_docs: pytorch-image-models/hfdocs/source - version_tag_suffix: '' \ No newline at end of file + version_tag_suffix: '' From c57239774c52081d413718433093f57c95ae7650 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 20:49:58 -0500 Subject: [PATCH 19/35] :construction: wip --- .github/workflows/build_pr_documentation.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index 0ea51e93d1..6add9077ae 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -17,4 +17,4 @@ jobs: package_name: timm repo_owner: rwightman path_to_docs: pytorch-image-models/hfdocs/source - version_tag_suffix: '' + version_tag_suffix: "" From e5dec9507e4191c033fcaa4fc19509c6d501e39c Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 21:02:29 -0500 Subject: [PATCH 20/35] :memo: add hf hub tutorial doc --- hfdocs/source/hf_hub.mdx | 53 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 52 insertions(+), 1 deletion(-) diff --git a/hfdocs/source/hf_hub.mdx b/hfdocs/source/hf_hub.mdx index e4f168b9d0..f4ac7fa97f 100644 --- a/hfdocs/source/hf_hub.mdx +++ b/hfdocs/source/hf_hub.mdx @@ -1,3 +1,54 @@ # Sharing and Loading Models From the Hugging Face Hub -TODO \ No newline at end of file +The `timm` library has a built-in integration with the Hugging Face Hub, making it easy to share and load models from the 🤗 Hub. + +In this short guide, we'll see how to: + 1. Share a `timm` model on the Hub + 2. How to load that model back from the Hub + +## Authenticating + +First, you'll need to make sure you have the `huggingface_hub` package installed. + +```bash +pip install huggingface_hub +``` + +Then, you'll need to authenticate yourself. You can do this by running the following command: + +```bash +huggingface-cli login +``` + +Or, if you're using a notebook, you can use the `notebook_login` helper: + +```py +>>> from huggingface_hub import notebook_login +>>> notebook_login() +``` + +## Sharing a Model + +```py +>>> import timm +>>> model = timm.create_model('resnet18', pretrained=True, num_classes=4) +``` + +Here is where you would normally train or fine-tune the model. We'll skip that for the sake of this tutorial. + +Let's pretend we've now fine-tuned the model. The next step would be to push it to the Hub! We can do this with the `timm.models.hub.push_to_hf_hub` function. + +```py +>>> model_cfg = dict(labels=['a', 'b', 'c', 'd']) +>>> timm.models.hub.push_to_hf_hub(model, 'resnet18-random', model_config=model_cfg) +``` + +Running the above would push the model to `/resnet18-random` on the Hub. You can now share this model with your friends, or use it in your own code! + +## Loading a Model + +Loading a model from the Hub is as simple as calling `timm.create_model` with the `pretrained` argument set to the name of the model you want to load. In this case, we'll use [`nateraw/resnet18-random`](https://huggingface.co/nateraw/resnet18-random), which is the model we just pushed to the Hub. + +```py +>>> model_reloaded = timm.create_model('hf_hub:nateraw/resnet18-random', pretrained=True) +``` From 8dc5830551f8a6a46dda0c8575f0d44592fb4201 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 21:04:46 -0500 Subject: [PATCH 21/35] :fire: remove inference tut --- hfdocs/source/_toctree.yml | 4 +--- hfdocs/source/inference.mdx | 3 --- 2 files changed, 1 insertion(+), 6 deletions(-) delete mode 100644 hfdocs/source/inference.mdx diff --git a/hfdocs/source/_toctree.yml b/hfdocs/source/_toctree.yml index 71fdcc6248..823e66c22c 100644 --- a/hfdocs/source/_toctree.yml +++ b/hfdocs/source/_toctree.yml @@ -7,14 +7,12 @@ title: Installation title: Get started - sections: - - local: inference - title: Using Pretrained Models for Inference - local: feature_extraction title: Using Pretrained Models as Feature Extractors - local: training_script title: Training With The Official Training Script - local: hf_hub - title: Share and Load Models from the Hugging Face Hub + title: Share and Load Models from the 🤗 Hugging Face Hub title: Tutorials - sections: - local: models/adversarial-inception-v3 diff --git a/hfdocs/source/inference.mdx b/hfdocs/source/inference.mdx deleted file mode 100644 index a31c31d53c..0000000000 --- a/hfdocs/source/inference.mdx +++ /dev/null @@ -1,3 +0,0 @@ -# Inference - -TODO \ No newline at end of file From c03e1fa042aa9e4fbbb13c059af0e6897735b176 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 21:11:00 -0500 Subject: [PATCH 22/35] :construction: wip --- .github/workflows/build_pr_documentation.yml | 1 - 1 file changed, 1 deletion(-) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index 6add9077ae..934a7acdd4 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -17,4 +17,3 @@ jobs: package_name: timm repo_owner: rwightman path_to_docs: pytorch-image-models/hfdocs/source - version_tag_suffix: "" From 7114867fc877cf6b8d4ac3ae7b3536eaeadccfbe Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 21:23:11 -0500 Subject: [PATCH 23/35] :memo: wip docs --- hfdocs/source/quickstart.mdx | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hfdocs/source/quickstart.mdx b/hfdocs/source/quickstart.mdx index 7c925101bd..2386766af2 100644 --- a/hfdocs/source/quickstart.mdx +++ b/hfdocs/source/quickstart.mdx @@ -10,7 +10,7 @@ pip install timm ## Load a Pretrained Model -Pretrained models can be loaded using `timm.create_model`. +Pretrained models can be loaded using [`create_model`]. Here, we load the pretrained `mobilenetv3_large_100` model. @@ -27,7 +27,7 @@ Here, we load the pretrained `mobilenetv3_large_100` model. ## List Models with Pretrained Weights -To list models packaged with `timm`, you can use `timm.list_models`. If you specify `pretrained=True`, this function will only return model names that have associated pretrained weights available. +To list models packaged with `timm`, you can use [`list_models`]. If you specify `pretrained=True`, this function will only return model names that have associated pretrained weights available. ```py >>> import timm @@ -136,7 +136,7 @@ We can then resolve only the data related configuration by using `timm.data.reso 'crop_pct': 0.875} ``` -We can pass this data config to timm.data.create_transform to initialize the model's associated transform. +We can pass this data config to [`timm.data.create_transform`] to initialize the model's associated transform. ```py >>> data_cfg = timm.data.resolve_data_config(model.pretrained_cfg) From 2f9f40130b51b83a24c880c0aa7ba14cdcdce893 Mon Sep 17 00:00:00 2001 From: nateraw Date: Mon, 5 Dec 2022 21:34:49 -0500 Subject: [PATCH 24/35] :memo: wip docs --- hfdocs/source/quickstart.mdx | 6 +++--- hfdocs/source/reference/data.mdx | 2 ++ 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/hfdocs/source/quickstart.mdx b/hfdocs/source/quickstart.mdx index 2386766af2..207710242c 100644 --- a/hfdocs/source/quickstart.mdx +++ b/hfdocs/source/quickstart.mdx @@ -22,7 +22,7 @@ Here, we load the pretrained `mobilenetv3_large_100` model. ``` -**Note:** The returned PyTorch model is set to `train` mode by default, so you must call `.eval()` on it if you plan to use it for inference. + Note: The returned PyTorch model is set to train mode by default, so you must call .eval() on it if you plan to use it for inference. ## List Models with Pretrained Weights @@ -92,7 +92,7 @@ torch.Size([1, 960, 7, 7]) ## Image Augmentation -To transform images into valid inputs for a model, you can use `timm.data.create_transform`, providing the desired `input_size` that the model expects. +To transform images into valid inputs for a model, you can use [`timm.data.create_transform`], providing the desired `input_size` that the model expects. This will return a generic transform that uses reasonable defaults. @@ -125,7 +125,7 @@ To figure out which transformations were used for a given pretrained model, we c 'architecture': 'mobilenetv3_large_100'} ``` -We can then resolve only the data related configuration by using `timm.data.resolve_data_config`. +We can then resolve only the data related configuration by using [`timm.data.resolve_data_config`]. ```py >>> timm.data.resolve_data_config(model.pretrained_cfg) diff --git a/hfdocs/source/reference/data.mdx b/hfdocs/source/reference/data.mdx index 0b00c9e3f1..b50487391e 100644 --- a/hfdocs/source/reference/data.mdx +++ b/hfdocs/source/reference/data.mdx @@ -5,3 +5,5 @@ [[autodoc]] timm.data.create_loader [[autodoc]] timm.data.create_transform + +[[autodoc]] timm.data.resolve_data_config \ No newline at end of file From 9076aa2087add404dd8a33ca16abb3056f9a4d51 Mon Sep 17 00:00:00 2001 From: nateraw Date: Tue, 13 Dec 2022 13:27:34 -0500 Subject: [PATCH 25/35] :memo: update docs --- hfdocs/source/_toctree.yml | 8 +- .../{optimization.mdx => optimizers.mdx} | 19 +--- hfdocs/source/reference/schedulers.mdx | 19 ++++ hfdocs/source/scripts.mdx | 35 ------ hfdocs/source/training_script.mdx | 101 +++++++++++++++++- 5 files changed, 123 insertions(+), 59 deletions(-) rename hfdocs/source/reference/{optimization.mdx => optimizers.mdx} (52%) create mode 100644 hfdocs/source/reference/schedulers.mdx delete mode 100644 hfdocs/source/scripts.mdx diff --git a/hfdocs/source/_toctree.yml b/hfdocs/source/_toctree.yml index 823e66c22c..56c42fe85a 100644 --- a/hfdocs/source/_toctree.yml +++ b/hfdocs/source/_toctree.yml @@ -148,16 +148,16 @@ title: Models - local: reference/data title: Data - - local: reference/optimization - title: Optimization + - local: reference/optimizers + title: Optimizers + - local: reference/schedulers + title: Learning Rate Schedulers title: Reference - sections: - local: models title: Model Summaries - local: results title: Results - - local: scripts - title: Scripts - local: training_hparam_examples title: Training Examples - local: changes diff --git a/hfdocs/source/reference/optimization.mdx b/hfdocs/source/reference/optimizers.mdx similarity index 52% rename from hfdocs/source/reference/optimization.mdx rename to hfdocs/source/reference/optimizers.mdx index 82c21bf631..637e7f0a74 100644 --- a/hfdocs/source/reference/optimization.mdx +++ b/hfdocs/source/reference/optimizers.mdx @@ -1,6 +1,6 @@ # Optimization -This page contains the API reference documentation for optimization-related tools (optimizers, learning rate schedulers, etc) included in `timm`. +This page contains the API reference documentation for learning rate optimizers included in `timm`. ## Optimizers @@ -25,20 +25,3 @@ This page contains the API reference documentation for optimization-related tool [[autodoc]] timm.optim.radam.RAdam [[autodoc]] timm.optim.rmsprop_tf.RMSpropTF [[autodoc]] timm.optim.sgdp.SGDP - - -## Schedulers - -### Factory functions - -[[autodoc]] timm.scheduler.scheduler_factory.create_scheduler -[[autodoc]] timm.scheduler.scheduler_factory.create_scheduler_v2 - -### Scheduler Classes - -[[autodoc]] timm.scheduler.cosine_lr.CosineLRScheduler -[[autodoc]] timm.scheduler.multistep_lr.MultiStepLRScheduler -[[autodoc]] timm.scheduler.plateau_lr.PlateauLRScheduler -[[autodoc]] timm.scheduler.poly_lr.PolyLRScheduler -[[autodoc]] timm.scheduler.step_lr.StepLRScheduler -[[autodoc]] timm.scheduler.tanh_lr.TanhLRScheduler diff --git a/hfdocs/source/reference/schedulers.mdx b/hfdocs/source/reference/schedulers.mdx new file mode 100644 index 0000000000..c44577d6a7 --- /dev/null +++ b/hfdocs/source/reference/schedulers.mdx @@ -0,0 +1,19 @@ +# Learning Rate Schedulers + +This page contains the API reference documentation for learning rate schedulers included in `timm`. + +## Schedulers + +### Factory functions + +[[autodoc]] timm.scheduler.scheduler_factory.create_scheduler +[[autodoc]] timm.scheduler.scheduler_factory.create_scheduler_v2 + +### Scheduler Classes + +[[autodoc]] timm.scheduler.cosine_lr.CosineLRScheduler +[[autodoc]] timm.scheduler.multistep_lr.MultiStepLRScheduler +[[autodoc]] timm.scheduler.plateau_lr.PlateauLRScheduler +[[autodoc]] timm.scheduler.poly_lr.PolyLRScheduler +[[autodoc]] timm.scheduler.step_lr.StepLRScheduler +[[autodoc]] timm.scheduler.tanh_lr.TanhLRScheduler diff --git a/hfdocs/source/scripts.mdx b/hfdocs/source/scripts.mdx deleted file mode 100644 index 46404d8135..0000000000 --- a/hfdocs/source/scripts.mdx +++ /dev/null @@ -1,35 +0,0 @@ -# Scripts -A train, validation, inference, and checkpoint cleaning script included in the github root folder. Scripts are not currently packaged in the pip release. - -The training and validation scripts evolved from early versions of the [PyTorch Imagenet Examples](https://github.com/pytorch/examples). I have added significant functionality over time, including CUDA specific performance enhancements based on -[NVIDIA's APEX Examples](https://github.com/NVIDIA/apex/tree/master/examples). - -## Training Script - -The variety of training args is large and not all combinations of options (or even options) have been fully tested. For the training dataset folder, specify the folder to the base that contains a `train` and `validation` folder. - -To train an SE-ResNet34 on ImageNet, locally distributed, 4 GPUs, one process per GPU w/ cosine schedule, random-erasing prob of 50% and per-pixel random value: - -```bash -./distributed_train.sh 4 /data/imagenet --model seresnet34 --sched cosine --epochs 150 --warmup-epochs 5 --lr 0.4 --reprob 0.5 --remode pixel --batch-size 256 --amp -j 4 -``` - - - It is recommended to use PyTorch 1.9+ w/ PyTorch native AMP and DDP instead of APEX AMP. --amp defaults to native AMP as of timm ver 0.4.3. --apex-amp will force use of APEX components if they are installed. - - -## Validation / Inference Scripts - -Validation and inference scripts are similar in usage. One outputs metrics on a validation set and the other outputs topk class ids in a csv. Specify the folder containing validation images, not the base as in training script. - -To validate with the model's pretrained weights (if they exist): - -```bash -python validate.py /imagenet/validation/ --model seresnext26_32x4d --pretrained -``` - -To run inference from a checkpoint: - -```bash -python inference.py /imagenet/validation/ --model mobilenetv3_large_100 --checkpoint ./output/train/model_best.pth.tar -``` \ No newline at end of file diff --git a/hfdocs/source/training_script.mdx b/hfdocs/source/training_script.mdx index 66cce8acdc..82e417ce99 100644 --- a/hfdocs/source/training_script.mdx +++ b/hfdocs/source/training_script.mdx @@ -1,3 +1,100 @@ -# Training Using the Official Training Script +# Scripts -TODO \ No newline at end of file +A train, validation, inference, and checkpoint cleaning script included in the github root folder. Scripts are not currently packaged in the pip release. + +The training and validation scripts evolved from early versions of the [PyTorch Imagenet Examples](https://github.com/pytorch/examples). I have added significant functionality over time, including CUDA specific performance enhancements based on +[NVIDIA's APEX Examples](https://github.com/NVIDIA/apex/tree/master/examples). + +## Training Script + +The variety of training args is large and not all combinations of options (or even options) have been fully tested. For the training dataset folder, specify the folder to the base that contains a `train` and `validation` folder. + +To train an SE-ResNet34 on ImageNet, locally distributed, 4 GPUs, one process per GPU w/ cosine schedule, random-erasing prob of 50% and per-pixel random value: + +```bash +./distributed_train.sh 4 /data/imagenet --model seresnet34 --sched cosine --epochs 150 --warmup-epochs 5 --lr 0.4 --reprob 0.5 --remode pixel --batch-size 256 --amp -j 4 +``` + + + It is recommended to use PyTorch 1.9+ w/ PyTorch native AMP and DDP instead of APEX AMP. --amp defaults to native AMP as of timm ver 0.4.3. --apex-amp will force use of APEX components if they are installed. + + +## Training Script Examples + +### EfficientNet-B2 with RandAugment - 80.4 top-1, 95.1 top-5 + +These params are for dual Titan RTX cards with NVIDIA Apex installed: + +```bash +./distributed_train.sh 2 /imagenet/ --model efficientnet_b2 -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .016 +``` + +### MixNet-XL with RandAugment - 80.5 top-1, 94.9 top-5 + +This params are for dual Titan RTX cards with NVIDIA Apex installed: + +```bash +./distributed_train.sh 2 /imagenet/ --model mixnet_xl -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .969 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.3 --amp --lr .016 --dist-bn reduce +``` + +### SE-ResNeXt-26-D and SE-ResNeXt-26-T + +These hparams (or similar) work well for a wide range of ResNet architecture, generally a good idea to increase the epoch # as the model size increases... ie approx 180-200 for ResNe(X)t50, and 220+ for larger. Increase batch size and LR proportionally for better GPUs or with AMP enabled. These params were for 2 1080Ti cards: + +```bash +./distributed_train.sh 2 /imagenet/ --model seresnext26t_32x4d --lr 0.1 --warmup-epochs 5 --epochs 160 --weight-decay 1e-4 --sched cosine --reprob 0.4 --remode pixel -b 112 +``` +### EfficientNet-B3 with RandAugment - 81.5 top-1, 95.7 top-5 + +The training of this model started with the same command line as EfficientNet-B2 w/ RA above. After almost three weeks of training the process crashed. The results weren't looking amazing so I resumed the training several times with tweaks to a few params (increase RE prob, decrease rand-aug, increase ema-decay). Nothing looked great. I ended up averaging the best checkpoints from all restarts. The result is mediocre at default res/crop but oddly performs much better with a full image test crop of 1.0. + +### EfficientNet-B0 with RandAugment - 77.7 top-1, 95.3 top-5 + +[Michael Klachko](https://github.com/michaelklachko) achieved these results with the command line for B2 adapted for larger batch size, with the recommended B0 dropout rate of 0.2. + +```bash +./distributed_train.sh 2 /imagenet/ --model efficientnet_b0 -b 384 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .048 +``` +### ResNet50 with JSD loss and RandAugment (clean + 2x RA augs) - 79.04 top-1, 94.39 top-5 + +Trained on two older 1080Ti cards, this took a while. Only slightly, non statistically better ImageNet validation result than my first good AugMix training of 78.99. However, these weights are more robust on tests with ImageNetV2, ImageNet-Sketch, etc. Unlike my first AugMix runs, I've enabled SplitBatchNorm, disabled random erasing on the clean split, and cranked up random erasing prob on the 2 augmented paths. + +```bash +./distributed_train.sh 2 /imagenet -b 64 --model resnet50 --sched cosine --epochs 200 --lr 0.05 --amp --remode pixel --reprob 0.6 --aug-splits 3 --aa rand-m9-mstd0.5-inc1 --resplit --split-bn --jsd --dist-bn reduce +``` +### EfficientNet-ES (EdgeTPU-Small) with RandAugment - 78.066 top-1, 93.926 top-5 + +Trained by [Andrew Lavin](https://github.com/andravin) with 8 V100 cards. Model EMA was not used, final checkpoint is the average of 8 best checkpoints during training. + +```bash +./distributed_train.sh 8 /imagenet --model efficientnet_es -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .064 +``` +### MobileNetV3-Large-100 - 75.766 top-1, 92,542 top-5 + +```bash +./distributed_train.sh 2 /imagenet/ --model mobilenetv3_large_100 -b 512 --sched step --epochs 600 --decay-epochs 2.4 --decay-rate .973 --opt rmsproptf --opt-eps .001 -j 7 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .064 --lr-noise 0.42 0.9 +``` + +### ResNeXt-50 32x4d w/ RandAugment - 79.762 top-1, 94.60 top-5 +These params will also work well for SE-ResNeXt-50 and SK-ResNeXt-50 and likely 101. I used them for the SK-ResNeXt-50 32x4d that I trained with 2 GPU using a slightly higher LR per effective batch size (lr=0.18, b=192 per GPU). The cmd line below are tuned for 8 GPU training. + + +```bash +./distributed_train.sh 8 /imagenet --model resnext50_32x4d --lr 0.6 --warmup-epochs 5 --epochs 240 --weight-decay 1e-4 --sched cosine --reprob 0.4 --recount 3 --remode pixel --aa rand-m7-mstd0.5-inc1 -b 192 -j 6 --amp --dist-bn reduce +``` + +## Validation / Inference Scripts + +Validation and inference scripts are similar in usage. One outputs metrics on a validation set and the other outputs topk class ids in a csv. Specify the folder containing validation images, not the base as in training script. + +To validate with the model's pretrained weights (if they exist): + +```bash +python validate.py /imagenet/validation/ --model seresnext26_32x4d --pretrained +``` + +To run inference from a checkpoint: + +```bash +python inference.py /imagenet/validation/ --model mobilenetv3_large_100 --checkpoint ./output/train/model_best.pth.tar +``` \ No newline at end of file From d654cb083863027d9c7c9652390d2f1fb7a8d782 Mon Sep 17 00:00:00 2001 From: nateraw Date: Tue, 13 Dec 2022 13:36:27 -0500 Subject: [PATCH 26/35] :memo: move validation script doc up in order --- hfdocs/source/training_script.mdx | 35 ++++++++++++++++--------------- 1 file changed, 18 insertions(+), 17 deletions(-) diff --git a/hfdocs/source/training_script.mdx b/hfdocs/source/training_script.mdx index 82e417ce99..3eb772a3c9 100644 --- a/hfdocs/source/training_script.mdx +++ b/hfdocs/source/training_script.mdx @@ -19,7 +19,24 @@ To train an SE-ResNet34 on ImageNet, locally distributed, 4 GPUs, one process pe It is recommended to use PyTorch 1.9+ w/ PyTorch native AMP and DDP instead of APEX AMP. --amp defaults to native AMP as of timm ver 0.4.3. --apex-amp will force use of APEX components if they are installed. -## Training Script Examples + +## Validation / Inference Scripts + +Validation and inference scripts are similar in usage. One outputs metrics on a validation set and the other outputs topk class ids in a csv. Specify the folder containing validation images, not the base as in training script. + +To validate with the model's pretrained weights (if they exist): + +```bash +python validate.py /imagenet/validation/ --model seresnext26_32x4d --pretrained +``` + +To run inference from a checkpoint: + +```bash +python inference.py /imagenet/validation/ --model mobilenetv3_large_100 --checkpoint ./output/train/model_best.pth.tar +``` + +## Training Examples ### EfficientNet-B2 with RandAugment - 80.4 top-1, 95.1 top-5 @@ -82,19 +99,3 @@ These params will also work well for SE-ResNeXt-50 and SK-ResNeXt-50 and likely ```bash ./distributed_train.sh 8 /imagenet --model resnext50_32x4d --lr 0.6 --warmup-epochs 5 --epochs 240 --weight-decay 1e-4 --sched cosine --reprob 0.4 --recount 3 --remode pixel --aa rand-m7-mstd0.5-inc1 -b 192 -j 6 --amp --dist-bn reduce ``` - -## Validation / Inference Scripts - -Validation and inference scripts are similar in usage. One outputs metrics on a validation set and the other outputs topk class ids in a csv. Specify the folder containing validation images, not the base as in training script. - -To validate with the model's pretrained weights (if they exist): - -```bash -python validate.py /imagenet/validation/ --model seresnext26_32x4d --pretrained -``` - -To run inference from a checkpoint: - -```bash -python inference.py /imagenet/validation/ --model mobilenetv3_large_100 --checkpoint ./output/train/model_best.pth.tar -``` \ No newline at end of file From 4b521be99967da7e8c65ff18f2ed40515ef2198f Mon Sep 17 00:00:00 2001 From: nateraw Date: Tue, 13 Dec 2022 13:39:46 -0500 Subject: [PATCH 27/35] :art: restructure to remove legacy docs --- hfdocs/source/_toctree.yml | 17 +- hfdocs/source/archived_changes.mdx | 418 --------------------- hfdocs/source/changes.mdx | 187 --------- hfdocs/source/training_hparam_examples.mdx | 63 ---- 4 files changed, 5 insertions(+), 680 deletions(-) delete mode 100644 hfdocs/source/archived_changes.mdx delete mode 100644 hfdocs/source/changes.mdx delete mode 100644 hfdocs/source/training_hparam_examples.mdx diff --git a/hfdocs/source/_toctree.yml b/hfdocs/source/_toctree.yml index 56c42fe85a..9af48fdcb5 100644 --- a/hfdocs/source/_toctree.yml +++ b/hfdocs/source/_toctree.yml @@ -15,6 +15,10 @@ title: Share and Load Models from the 🤗 Hugging Face Hub title: Tutorials - sections: + - local: models + title: Model Summaries + - local: results + title: Results - local: models/adversarial-inception-v3 title: Adversarial Inception v3 - local: models/advprop @@ -153,15 +157,4 @@ - local: reference/schedulers title: Learning Rate Schedulers title: Reference -- sections: - - local: models - title: Model Summaries - - local: results - title: Results - - local: training_hparam_examples - title: Training Examples - - local: changes - title: Recent Changes - - local: archived_changes - title: Archived Changes - title: Legacy Docs + diff --git a/hfdocs/source/archived_changes.mdx b/hfdocs/source/archived_changes.mdx deleted file mode 100644 index 2577856250..0000000000 --- a/hfdocs/source/archived_changes.mdx +++ /dev/null @@ -1,418 +0,0 @@ -# Archived Changes - -### July 12, 2021 - -* Add XCiT models from [official facebook impl](https://github.com/facebookresearch/xcit). Contributed by [Alexander Soare](https://github.com/alexander-soare) - -### July 5-9, 2021 - -* Add `efficientnetv2_rw_t` weights, a custom 'tiny' 13.6M param variant that is a bit better than (non NoisyStudent) B3 models. Both faster and better accuracy (at same or lower res) - * top-1 82.34 @ 288x288 and 82.54 @ 320x320 -* Add [SAM pretrained](https://arxiv.org/abs/2106.01548) in1k weight for ViT B/16 (`vit_base_patch16_sam_224`) and B/32 (`vit_base_patch32_sam_224`) models. -* Add 'Aggregating Nested Transformer' (NesT) w/ weights converted from official [Flax impl](https://github.com/google-research/nested-transformer). Contributed by [Alexander Soare](https://github.com/alexander-soare). - * `jx_nest_base` - 83.534, `jx_nest_small` - 83.120, `jx_nest_tiny` - 81.426 - -### June 23, 2021 - -* Reproduce gMLP model training, `gmlp_s16_224` trained to 79.6 top-1, matching [paper](https://arxiv.org/abs/2105.08050). Hparams for this and other recent MLP training [here](https://gist.github.com/rwightman/d6c264a9001f9167e06c209f630b2cc6) - -### June 20, 2021 - -* Release Vision Transformer 'AugReg' weights from [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://arxiv.org/abs/2106.10270) - * .npz weight loading support added, can load any of the 50K+ weights from the [AugReg series](https://console.cloud.google.com/storage/browser/vit_models/augreg) - * See [example notebook](https://colab.research.google.com/github/google-research/vision_transformer/blob/master/vit_jax_augreg.ipynb) from [official impl](https://github.com/google-research/vision_transformer/) for navigating the augreg weights - * Replaced all default weights w/ best AugReg variant (if possible). All AugReg 21k classifiers work. - * Highlights: `vit_large_patch16_384` (87.1 top-1), `vit_large_r50_s32_384` (86.2 top-1), `vit_base_patch16_384` (86.0 top-1) - * `vit_deit_*` renamed to just `deit_*` - * Remove my old small model, replace with DeiT compatible small w/ AugReg weights -* Add 1st training of my `gmixer_24_224` MLP /w GLU, 78.1 top-1 w/ 25M params. -* Add weights from official ResMLP release (https://github.com/facebookresearch/deit) -* Add `eca_nfnet_l2` weights from my 'lightweight' series. 84.7 top-1 at 384x384. -* Add distilled BiT 50x1 student and 152x2 Teacher weights from [Knowledge distillation: A good teacher is patient and consistent](https://arxiv.org/abs/2106.05237) -* NFNets and ResNetV2-BiT models work w/ Pytorch XLA now - * weight standardization uses F.batch_norm instead of std_mean (std_mean wasn't lowered) - * eps values adjusted, will be slight differences but should be quite close -* Improve test coverage and classifier interface of non-conv (vision transformer and mlp) models -* Cleanup a few classifier / flatten details for models w/ conv classifiers or early global pool -* Please report any regressions, this PR touched quite a few models. - -### June 8, 2021 - -* Add first ResMLP weights, trained in PyTorch XLA on TPU-VM w/ my XLA branch. 24 block variant, 79.2 top-1. -* Add ResNet51-Q model w/ pretrained weights at 82.36 top-1. - * NFNet inspired block layout with quad layer stem and no maxpool - * Same param count (35.7M) and throughput as ResNetRS-50 but +1.5 top-1 @ 224x224 and +2.5 top-1 at 288x288 - -### May 25, 2021 - -* Add LeViT, Visformer, Convit (PR by Aman Arora), Twins (PR by paper authors) transformer models -* Cleanup input_size/img_size override handling and testing for all vision transformer models -* Add `efficientnetv2_rw_m` model and weights (started training before official code). 84.8 top-1, 53M params. - -### May 14, 2021 - -* Add EfficientNet-V2 official model defs w/ ported weights from official [Tensorflow/Keras](https://github.com/google/automl/tree/master/efficientnetv2) impl. - * 1k trained variants: `tf_efficientnetv2_s/m/l` - * 21k trained variants: `tf_efficientnetv2_s/m/l_in21k` - * 21k pretrained -> 1k fine-tuned: `tf_efficientnetv2_s/m/l_in21ft1k` - * v2 models w/ v1 scaling: `tf_efficientnetv2_b0` through `b3` - * Rename my prev V2 guess `efficientnet_v2s` -> `efficientnetv2_rw_s` - * Some blank `efficientnetv2_*` models in-place for future native PyTorch training - -### May 5, 2021 - -* Add MLP-Mixer models and port pretrained weights from [Google JAX impl](https://github.com/google-research/vision_transformer/tree/linen) -* Add CaiT models and pretrained weights from [FB](https://github.com/facebookresearch/deit) -* Add ResNet-RS models and weights from [TF](https://github.com/tensorflow/tpu/tree/master/models/official/resnet/resnet_rs). Thanks [Aman Arora](https://github.com/amaarora) -* Add CoaT models and weights. Thanks [Mohammed Rizin](https://github.com/morizin) -* Add new ImageNet-21k weights & finetuned weights for TResNet, MobileNet-V3, ViT models. Thanks [mrT](https://github.com/mrT23) -* Add GhostNet models and weights. Thanks [Kai Han](https://github.com/iamhankai) -* Update ByoaNet attention modles - * Improve SA module inits - * Hack together experimental stand-alone Swin based attn module and `swinnet` - * Consistent '26t' model defs for experiments. -* Add improved Efficientnet-V2S (prelim model def) weights. 83.8 top-1. -* WandB logging support - -### April 13, 2021 - -* Add Swin Transformer models and weights from https://github.com/microsoft/Swin-Transformer - -### April 12, 2021 - -* Add ECA-NFNet-L1 (slimmed down F1 w/ SiLU, 41M params) trained with this code. 84% top-1 @ 320x320. Trained at 256x256. -* Add EfficientNet-V2S model (unverified model definition) weights. 83.3 top-1 @ 288x288. Only trained single res 224. Working on progressive training. -* Add ByoaNet model definition (Bring-your-own-attention) w/ SelfAttention block and corresponding SA/SA-like modules and model defs - * Lambda Networks - https://arxiv.org/abs/2102.08602 - * Bottleneck Transformers - https://arxiv.org/abs/2101.11605 - * Halo Nets - https://arxiv.org/abs/2103.12731 -* Adabelief optimizer contributed by Juntang Zhuang - -### April 1, 2021 - -* Add snazzy `benchmark.py` script for bulk `timm` model benchmarking of train and/or inference -* Add Pooling-based Vision Transformer (PiT) models (from https://github.com/naver-ai/pit) - * Merged distilled variant into main for torchscript compatibility - * Some `timm` cleanup/style tweaks and weights have hub download support -* Cleanup Vision Transformer (ViT) models - * Merge distilled (DeiT) model into main so that torchscript can work - * Support updated weight init (defaults to old still) that closer matches original JAX impl (possibly better training from scratch) - * Separate hybrid model defs into different file and add several new model defs to fiddle with, support patch_size != 1 for hybrids - * Fix fine-tuning num_class changes (PiT and ViT) and pos_embed resizing (Vit) with distilled variants - * nn.Sequential for block stack (does not break downstream compat) -* TnT (Transformer-in-Transformer) models contributed by author (from https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/cv/TNT) -* Add RegNetY-160 weights from DeiT teacher model -* Add new NFNet-L0 w/ SE attn (rename `nfnet_l0b`->`nfnet_l0`) weights 82.75 top-1 @ 288x288 -* Some fixes/improvements for TFDS dataset wrapper - -### March 7, 2021 - -* First 0.4.x PyPi release w/ NFNets (& related), ByoB (GPU-Efficient, RepVGG, etc). -* Change feature extraction for pre-activation nets (NFNets, ResNetV2) to return features before activation. - -### Feb 18, 2021 - -* Add pretrained weights and model variants for NFNet-F* models from [DeepMind Haiku impl](https://github.com/deepmind/deepmind-research/tree/master/nfnets). - * Models are prefixed with `dm_`. They require SAME padding conv, skipinit enabled, and activation gains applied in act fn. - * These models are big, expect to run out of GPU memory. With the GELU activiation + other options, they are roughly 1/2 the inference speed of my SiLU PyTorch optimized `s` variants. - * Original model results are based on pre-processing that is not the same as all other models so you'll see different results in the results csv (once updated). - * Matching the original pre-processing as closely as possible I get these results: - * `dm_nfnet_f6` - 86.352 - * `dm_nfnet_f5` - 86.100 - * `dm_nfnet_f4` - 85.834 - * `dm_nfnet_f3` - 85.676 - * `dm_nfnet_f2` - 85.178 - * `dm_nfnet_f1` - 84.696 - * `dm_nfnet_f0` - 83.464 - -### Feb 16, 2021 - -* Add Adaptive Gradient Clipping (AGC) as per https://arxiv.org/abs/2102.06171. Integrated w/ PyTorch gradient clipping via mode arg that defaults to prev 'norm' mode. For backward arg compat, clip-grad arg must be specified to enable when using train.py. - * AGC w/ default clipping factor `--clip-grad .01 --clip-mode agc` - * PyTorch global norm of 1.0 (old behaviour, always norm), `--clip-grad 1.0` - * PyTorch value clipping of 10, `--clip-grad 10. --clip-mode value` - * AGC performance is definitely sensitive to the clipping factor. More experimentation needed to determine good values for smaller batch sizes and optimizers besides those in paper. So far I've found .001-.005 is necessary for stable RMSProp training w/ NFNet/NF-ResNet. - -### Feb 12, 2021 - -* Update Normalization-Free nets to include new NFNet-F (https://arxiv.org/abs/2102.06171) model defs - -### Feb 10, 2021 - -* More model archs, incl a flexible ByobNet backbone ('Bring-your-own-blocks') - * GPU-Efficient-Networks (https://github.com/idstcv/GPU-Efficient-Networks), impl in `byobnet.py` - * RepVGG (https://github.com/DingXiaoH/RepVGG), impl in `byobnet.py` - * classic VGG (from torchvision, impl in `vgg`) -* Refinements to normalizer layer arg handling and normalizer+act layer handling in some models -* Default AMP mode changed to native PyTorch AMP instead of APEX. Issues not being fixed with APEX. Native works with `--channels-last` and `--torchscript` model training, APEX does not. -* Fix a few bugs introduced since last pypi release - -### Feb 8, 2021 - -* Add several ResNet weights with ECA attention. 26t & 50t trained @ 256, test @ 320. 269d train @ 256, fine-tune @320, test @ 352. - * `ecaresnet26t` - 79.88 top-1 @ 320x320, 79.08 @ 256x256 - * `ecaresnet50t` - 82.35 top-1 @ 320x320, 81.52 @ 256x256 - * `ecaresnet269d` - 84.93 top-1 @ 352x352, 84.87 @ 320x320 -* Remove separate tiered (`t`) vs tiered_narrow (`tn`) ResNet model defs, all `tn` changed to `t` and `t` models removed (`seresnext26t_32x4d` only model w/ weights that was removed). -* Support model default_cfgs with separate train vs test resolution `test_input_size` and remove extra `_320` suffix ResNet model defs that were just for test. - -### Jan 30, 2021 - -* Add initial "Normalization Free" NF-RegNet-B* and NF-ResNet model definitions based on [paper](https://arxiv.org/abs/2101.08692) - -### Jan 25, 2021 - -* Add ResNetV2 Big Transfer (BiT) models w/ ImageNet-1k and 21k weights from https://github.com/google-research/big_transfer -* Add official R50+ViT-B/16 hybrid models + weights from https://github.com/google-research/vision_transformer -* ImageNet-21k ViT weights are added w/ model defs and representation layer (pre logits) support - * NOTE: ImageNet-21k classifier heads were zero'd in original weights, they are only useful for transfer learning -* Add model defs and weights for DeiT Vision Transformer models from https://github.com/facebookresearch/deit -* Refactor dataset classes into ImageDataset/IterableImageDataset + dataset specific parser classes -* Add Tensorflow-Datasets (TFDS) wrapper to allow use of TFDS image classification sets with train script - * Ex: `train.py /data/tfds --dataset tfds/oxford_iiit_pet --val-split test --model resnet50 -b 256 --amp --num-classes 37 --opt adamw --lr 3e-4 --weight-decay .001 --pretrained -j 2` -* Add improved .tar dataset parser that reads images from .tar, folder of .tar files, or .tar within .tar - * Run validation on full ImageNet-21k directly from tar w/ BiT model: `validate.py /data/fall11_whole.tar --model resnetv2_50x1_bitm_in21k --amp` -* Models in this update should be stable w/ possible exception of ViT/BiT, possibility of some regressions with train/val scripts and dataset handling - -### Jan 3, 2021 - -* Add SE-ResNet-152D weights - * 256x256 val, 0.94 crop top-1 - 83.75 - * 320x320 val, 1.0 crop - 84.36 -* Update results files - -### Dec 18, 2020 - -* Add ResNet-101D, ResNet-152D, and ResNet-200D weights trained @ 256x256 - * 256x256 val, 0.94 crop (top-1) - 101D (82.33), 152D (83.08), 200D (83.25) - * 288x288 val, 1.0 crop - 101D (82.64), 152D (83.48), 200D (83.76) - * 320x320 val, 1.0 crop - 101D (83.00), 152D (83.66), 200D (84.01) - -### Dec 7, 2020 - -* Simplify EMA module (ModelEmaV2), compatible with fully torchscripted models -* Misc fixes for SiLU ONNX export, default_cfg missing from Feature extraction models, Linear layer w/ AMP + torchscript -* PyPi release @ 0.3.2 (needed by EfficientDet) - - -### Oct 30, 2020 - -* Test with PyTorch 1.7 and fix a small top-n metric view vs reshape issue. -* Convert newly added 224x224 Vision Transformer weights from official JAX repo. 81.8 top-1 for B/16, 83.1 L/16. -* Support PyTorch 1.7 optimized, native SiLU (aka Swish) activation. Add mapping to 'silu' name, custom swish will eventually be deprecated. -* Fix regression for loading pretrained classifier via direct model entrypoint functions. Didn't impact create_model() factory usage. -* PyPi release @ 0.3.0 version! - -### Oct 26, 2020 - -* Update Vision Transformer models to be compatible with official code release at https://github.com/google-research/vision_transformer -* Add Vision Transformer weights (ImageNet-21k pretrain) for 384x384 base and large models converted from official jax impl - * ViT-B/16 - 84.2 - * ViT-B/32 - 81.7 - * ViT-L/16 - 85.2 - * ViT-L/32 - 81.5 - -### Oct 21, 2020 - -* Weights added for Vision Transformer (ViT) models. 77.86 top-1 for 'small' and 79.35 for 'base'. Thanks to [Christof](https://www.kaggle.com/christofhenkel) for training the base model w/ lots of GPUs. - -### Oct 13, 2020 - -* Initial impl of Vision Transformer models. Both patch and hybrid (CNN backbone) variants. Currently trying to train... -* Adafactor and AdaHessian (FP32 only, no AMP) optimizers -* EdgeTPU-M (`efficientnet_em`) model trained in PyTorch, 79.3 top-1 -* Pip release, doc updates pending a few more changes... - -### Sept 18, 2020 - -* New ResNet 'D' weights. 72.7 (top-1) ResNet-18-D, 77.1 ResNet-34-D, 80.5 ResNet-50-D -* Added a few untrained defs for other ResNet models (66D, 101D, 152D, 200/200D) - -### Sept 3, 2020 - -* New weights - * Wide-ResNet50 - 81.5 top-1 (vs 78.5 torchvision) - * SEResNeXt50-32x4d - 81.3 top-1 (vs 79.1 cadene) -* Support for native Torch AMP and channels_last memory format added to train/validate scripts (`--channels-last`, `--native-amp` vs `--apex-amp`) -* Models tested with channels_last on latest NGC 20.08 container. AdaptiveAvgPool in attn layers changed to mean((2,3)) to work around bug with NHWC kernel. - -### Aug 12, 2020 - -* New/updated weights from training experiments - * EfficientNet-B3 - 82.1 top-1 (vs 81.6 for official with AA and 81.9 for AdvProp) - * RegNetY-3.2GF - 82.0 top-1 (78.9 from official ver) - * CSPResNet50 - 79.6 top-1 (76.6 from official ver) -* Add CutMix integrated w/ Mixup. See [pull request](https://github.com/rwightman/pytorch-image-models/pull/218) for some usage examples -* Some fixes for using pretrained weights with `in_chans` != 3 on several models. - -### Aug 5, 2020 - -Universal feature extraction, new models, new weights, new test sets. -* All models support the `features_only=True` argument for `create_model` call to return a network that extracts feature maps from the deepest layer at each stride. -* New models - * CSPResNet, CSPResNeXt, CSPDarkNet, DarkNet - * ReXNet - * (Modified Aligned) Xception41/65/71 (a proper port of TF models) -* New trained weights - * SEResNet50 - 80.3 top-1 - * CSPDarkNet53 - 80.1 top-1 - * CSPResNeXt50 - 80.0 top-1 - * DPN68b - 79.2 top-1 - * EfficientNet-Lite0 (non-TF ver) - 75.5 (submitted by [@hal-314](https://github.com/hal-314)) -* Add 'real' labels for ImageNet and ImageNet-Renditions test set, see [`results/README.md`](results/README.md) -* Test set ranking/top-n diff script by [@KushajveerSingh](https://github.com/KushajveerSingh) -* Train script and loader/transform tweaks to punch through more aug arguments -* README and documentation overhaul. See initial (WIP) documentation at https://rwightman.github.io/pytorch-image-models/ -* adamp and sgdp optimizers added by [@hellbell](https://github.com/hellbell) - -### June 11, 2020 - -Bunch of changes: -* DenseNet models updated with memory efficient addition from torchvision (fixed a bug), blur pooling and deep stem additions -* VoVNet V1 and V2 models added, 39 V2 variant (ese_vovnet_39b) trained to 79.3 top-1 -* Activation factory added along with new activations: - * select act at model creation time for more flexibility in using activations compatible with scripting or tracing (ONNX export) - * hard_mish (experimental) added with memory-efficient grad, along with ME hard_swish - * context mgr for setting exportable/scriptable/no_jit states -* Norm + Activation combo layers added with initial trial support in DenseNet and VoVNet along with impl of EvoNorm and InplaceAbn wrapper that fit the interface -* Torchscript works for all but two of the model types as long as using Pytorch 1.5+, tests added for this -* Some import cleanup and classifier reset changes, all models will have classifier reset to nn.Identity on reset_classifer(0) call -* Prep for 0.1.28 pip release - -### May 12, 2020 - -* Add ResNeSt models (code adapted from https://github.com/zhanghang1989/ResNeSt, paper https://arxiv.org/abs/2004.08955)) - -### May 3, 2020 - -* Pruned EfficientNet B1, B2, and B3 (https://arxiv.org/abs/2002.08258) contributed by [Yonathan Aflalo](https://github.com/yoniaflalo) - -### May 1, 2020 - -* Merged a number of execellent contributions in the ResNet model family over the past month - * BlurPool2D and resnetblur models initiated by [Chris Ha](https://github.com/VRandme), I trained resnetblur50 to 79.3. - * TResNet models and SpaceToDepth, AntiAliasDownsampleLayer layers by [mrT23](https://github.com/mrT23) - * ecaresnet (50d, 101d, light) models and two pruned variants using pruning as per (https://arxiv.org/abs/2002.08258) by [Yonathan Aflalo](https://github.com/yoniaflalo) -* 200 pretrained models in total now with updated results csv in results folder - -### April 5, 2020 - -* Add some newly trained MobileNet-V2 models trained with latest h-params, rand augment. They compare quite favourably to EfficientNet-Lite - * 3.5M param MobileNet-V2 100 @ 73% - * 4.5M param MobileNet-V2 110d @ 75% - * 6.1M param MobileNet-V2 140 @ 76.5% - * 5.8M param MobileNet-V2 120d @ 77.3% - -### March 18, 2020 - -* Add EfficientNet-Lite models w/ weights ported from [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite) -* Add RandAugment trained ResNeXt-50 32x4d weights with 79.8 top-1. Trained by [Andrew Lavin](https://github.com/andravin) (see Training section for hparams) - -### April 5, 2020 - -* Add some newly trained MobileNet-V2 models trained with latest h-params, rand augment. They compare quite favourably to EfficientNet-Lite - * 3.5M param MobileNet-V2 100 @ 73% - * 4.5M param MobileNet-V2 110d @ 75% - * 6.1M param MobileNet-V2 140 @ 76.5% - * 5.8M param MobileNet-V2 120d @ 77.3% - -### March 18, 2020 - -* Add EfficientNet-Lite models w/ weights ported from [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite) -* Add RandAugment trained ResNeXt-50 32x4d weights with 79.8 top-1. Trained by [Andrew Lavin](https://github.com/andravin) (see Training section for hparams) - -### Feb 29, 2020 - -* New MobileNet-V3 Large weights trained from stratch with this code to 75.77% top-1 -* IMPORTANT CHANGE - default weight init changed for all MobilenetV3 / EfficientNet / related models - * overall results similar to a bit better training from scratch on a few smaller models tried - * performance early in training seems consistently improved but less difference by end - * set `fix_group_fanout=False` in `_init_weight_goog` fn if you need to reproducte past behaviour -* Experimental LR noise feature added applies a random perturbation to LR each epoch in specified range of training - -### Feb 18, 2020 - -* Big refactor of model layers and addition of several attention mechanisms. Several additions motivated by 'Compounding the Performance Improvements...' (https://arxiv.org/abs/2001.06268): - * Move layer/module impl into `layers` subfolder/module of `models` and organize in a more granular fashion - * ResNet downsample paths now properly support dilation (output stride != 32) for avg_pool ('D' variant) and 3x3 (SENets) networks - * Add Selective Kernel Nets on top of ResNet base, pretrained weights - * skresnet18 - 73% top-1 - * skresnet34 - 76.9% top-1 - * skresnext50_32x4d (equiv to SKNet50) - 80.2% top-1 - * ECA and CECA (circular padding) attention layer contributed by [Chris Ha](https://github.com/VRandme) - * CBAM attention experiment (not the best results so far, may remove) - * Attention factory to allow dynamically selecting one of SE, ECA, CBAM in the `.se` position for all ResNets - * Add DropBlock and DropPath (formerly DropConnect for EfficientNet/MobileNetv3) support to all ResNet variants -* Full dataset results updated that incl NoisyStudent weights and 2 of the 3 SK weights - -### Feb 12, 2020 - -* Add EfficientNet-L2 and B0-B7 NoisyStudent weights ported from [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) - -### Feb 6, 2020 - -* Add RandAugment trained EfficientNet-ES (EdgeTPU-Small) weights with 78.1 top-1. Trained by [Andrew Lavin](https://github.com/andravin) (see Training section for hparams) - -### Feb 1/2, 2020 - -* Port new EfficientNet-B8 (RandAugment) weights, these are different than the B8 AdvProp, different input normalization. -* Update results csv files on all models for ImageNet validation and three other test sets -* Push PyPi package update - -### Jan 31, 2020 - -* Update ResNet50 weights with a new 79.038 result from further JSD / AugMix experiments. Full command line for reproduction in training section below. - -### Jan 11/12, 2020 - -* Master may be a bit unstable wrt to training, these changes have been tested but not all combos -* Implementations of AugMix added to existing RA and AA. Including numerous supporting pieces like JSD loss (Jensen-Shannon divergence + CE), and AugMixDataset -* SplitBatchNorm adaptation layer added for implementing Auxiliary BN as per AdvProp paper -* ResNet-50 AugMix trained model w/ 79% top-1 added -* `seresnext26tn_32x4d` - 77.99 top-1, 93.75 top-5 added to tiered experiment, higher img/s than 't' and 'd' - -### Jan 3, 2020 - -* Add RandAugment trained EfficientNet-B0 weight with 77.7 top-1. Trained by [Michael Klachko](https://github.com/michaelklachko) with this code and recent hparams (see Training section) -* Add `avg_checkpoints.py` script for post training weight averaging and update all scripts with header docstrings and shebangs. - -### Dec 30, 2019 - -* Merge [Dushyant Mehta's](https://github.com/mehtadushy) PR for SelecSLS (Selective Short and Long Range Skip Connections) networks. Good GPU memory consumption and throughput. Original: https://github.com/mehtadushy/SelecSLS-Pytorch - -### Dec 28, 2019 - -* Add new model weights and training hparams (see Training Hparams section) - * `efficientnet_b3` - 81.5 top-1, 95.7 top-5 at default res/crop, 81.9, 95.8 at 320x320 1.0 crop-pct - * trained with RandAugment, ended up with an interesting but less than perfect result (see training section) - * `seresnext26d_32x4d`- 77.6 top-1, 93.6 top-5 - * deep stem (32, 32, 64), avgpool downsample - * stem/dowsample from bag-of-tricks paper - * `seresnext26t_32x4d`- 78.0 top-1, 93.7 top-5 - * deep tiered stem (24, 48, 64), avgpool downsample (a modified 'D' variant) - * stem sizing mods from Jeremy Howard and fastai devs discussing ResNet architecture experiments - -### Dec 23, 2019 - -* Add RandAugment trained MixNet-XL weights with 80.48 top-1. -* `--dist-bn` argument added to train.py, will distribute BN stats between nodes after each train epoch, before eval - -### Dec 4, 2019 - -* Added weights from the first training from scratch of an EfficientNet (B2) with my new RandAugment implementation. Much better than my previous B2 and very close to the official AdvProp ones (80.4 top-1, 95.08 top-5). - -### Nov 29, 2019 - -* Brought EfficientNet and MobileNetV3 up to date with my https://github.com/rwightman/gen-efficientnet-pytorch code. Torchscript and ONNX export compat excluded. - * AdvProp weights added - * Official TF MobileNetv3 weights added -* EfficientNet and MobileNetV3 hook based 'feature extraction' classes added. Will serve as basis for using models as backbones in obj detection/segmentation tasks. Lots more to be done here... -* HRNet classification models and weights added from https://github.com/HRNet/HRNet-Image-Classification -* Consistency in global pooling, `reset_classifer`, and `forward_features` across models - * `forward_features` always returns unpooled feature maps now -* Reasonable chance I broke something... let me know - -### Nov 22, 2019 - -* Add ImageNet training RandAugment implementation alongside AutoAugment. PyTorch Transform compatible format, using PIL. Currently training two EfficientNet models from scratch with promising results... will update. -* `drop-connect` cmd line arg finally added to `train.py`, no need to hack model fns. Works for efficientnet/mobilenetv3 based models, ignored otherwise. \ No newline at end of file diff --git a/hfdocs/source/changes.mdx b/hfdocs/source/changes.mdx deleted file mode 100644 index 93dc9fac20..0000000000 --- a/hfdocs/source/changes.mdx +++ /dev/null @@ -1,187 +0,0 @@ -# Recent Changes - -### July 27, 2022 - -* All runtime benchmark and validation result csv files are up-to-date! -* A few more weights & model defs added: - * `darknetaa53` - 79.8 @ 256, 80.5 @ 288 - * `convnext_nano` - 80.8 @ 224, 81.5 @ 288 - * `cs3sedarknet_l` - 81.2 @ 256, 81.8 @ 288 - * `cs3darknet_x` - 81.8 @ 256, 82.2 @ 288 - * `cs3sedarknet_x` - 82.2 @ 256, 82.7 @ 288 - * `cs3edgenet_x` - 82.2 @ 256, 82.7 @ 288 - * `cs3se_edgenet_x` - 82.8 @ 256, 83.5 @ 320 -* `cs3*` weights above all trained on TPU w/ `bits_and_tpu` branch. Thanks to TRC program! -* Add output_stride=8 and 16 support to ConvNeXt (dilation) -* deit3 models not being able to resize pos_emb fixed -* Version 0.6.7 PyPi release (/w above bug fixes and new weighs since 0.6.5) - -### July 8, 2022 - -More models, more fixes - -* Official research models (w/ weights) added: - * EdgeNeXt from (https://github.com/mmaaz60/EdgeNeXt) - * MobileViT-V2 from (https://github.com/apple/ml-cvnets) - * DeiT III (Revenge of the ViT) from (https://github.com/facebookresearch/deit) -* My own models: - * Small `ResNet` defs added by request with 1 block repeats for both basic and bottleneck (resnet10 and resnet14) - * `CspNet` refactored with dataclass config, simplified CrossStage3 (`cs3`) option. These are closer to YOLO-v5+ backbone defs. - * More relative position vit fiddling. Two `srelpos` (shared relative position) models trained, and a medium w/ class token. - * Add an alternate downsample mode to EdgeNeXt and train a `small` model. Better than original small, but not their new USI trained weights. -* My own model weight results (all ImageNet-1k training) - * `resnet10t` - 66.5 @ 176, 68.3 @ 224 - * `resnet14t` - 71.3 @ 176, 72.3 @ 224 - * `resnetaa50` - 80.6 @ 224 , 81.6 @ 288 - * `darknet53` - 80.0 @ 256, 80.5 @ 288 - * `cs3darknet_m` - 77.0 @ 256, 77.6 @ 288 - * `cs3darknet_focus_m` - 76.7 @ 256, 77.3 @ 288 - * `cs3darknet_l` - 80.4 @ 256, 80.9 @ 288 - * `cs3darknet_focus_l` - 80.3 @ 256, 80.9 @ 288 - * `vit_srelpos_small_patch16_224` - 81.1 @ 224, 82.1 @ 320 - * `vit_srelpos_medium_patch16_224` - 82.3 @ 224, 83.1 @ 320 - * `vit_relpos_small_patch16_cls_224` - 82.6 @ 224, 83.6 @ 320 - * `edgnext_small_rw` - 79.6 @ 224, 80.4 @ 320 -* `cs3`, `darknet`, and `vit_*relpos` weights above all trained on TPU thanks to TRC program! Rest trained on overheating GPUs. -* Hugging Face Hub support fixes verified, demo notebook TBA -* Pretrained weights / configs can be loaded externally (ie from local disk) w/ support for head adaptation. -* Add support to change image extensions scanned by `timm` datasets/parsers. See (https://github.com/rwightman/pytorch-image-models/pull/1274#issuecomment-1178303103) -* Default ConvNeXt LayerNorm impl to use `F.layer_norm(x.permute(0, 2, 3, 1), ...).permute(0, 3, 1, 2)` via `LayerNorm2d` in all cases. - * a bit slower than previous custom impl on some hardware (ie Ampere w/ CL), but overall fewer regressions across wider HW / PyTorch version ranges. - * previous impl exists as `LayerNormExp2d` in `models/layers/norm.py` -* Numerous bug fixes -* Currently testing for imminent PyPi 0.6.x release -* LeViT pretraining of larger models still a WIP, they don't train well / easily without distillation. Time to add distill support (finally)? -* ImageNet-22k weight training + finetune ongoing, work on multi-weight support (slowly) chugging along (there are a LOT of weights, sigh) ... - -### May 13, 2022 - -* Official Swin-V2 models and weights added from (https://github.com/microsoft/Swin-Transformer). Cleaned up to support torchscript. -* Some refactoring for existing `timm` Swin-V2-CR impl, will likely do a bit more to bring parts closer to official and decide whether to merge some aspects. -* More Vision Transformer relative position / residual post-norm experiments (all trained on TPU thanks to TRC program) - * `vit_relpos_small_patch16_224` - 81.5 @ 224, 82.5 @ 320 -- rel pos, layer scale, no class token, avg pool - * `vit_relpos_medium_patch16_rpn_224` - 82.3 @ 224, 83.1 @ 320 -- rel pos + res-post-norm, no class token, avg pool - * `vit_relpos_medium_patch16_224` - 82.5 @ 224, 83.3 @ 320 -- rel pos, layer scale, no class token, avg pool - * `vit_relpos_base_patch16_gapcls_224` - 82.8 @ 224, 83.9 @ 320 -- rel pos, layer scale, class token, avg pool (by mistake) -* Bring 512 dim, 8-head 'medium' ViT model variant back to life (after using in a pre DeiT 'small' model for first ViT impl back in 2020) -* Add ViT relative position support for switching btw existing impl and some additions in official Swin-V2 impl for future trials -* Sequencer2D impl (https://arxiv.org/abs/2205.01972), added via PR from author (https://github.com/okojoalg) - -### May 2, 2022 - -* Vision Transformer experiments adding Relative Position (Swin-V2 log-coord) (`vision_transformer_relpos.py`) and Residual Post-Norm branches (from Swin-V2) (`vision_transformer*.py`) - * `vit_relpos_base_patch32_plus_rpn_256` - 79.5 @ 256, 80.6 @ 320 -- rel pos + extended width + res-post-norm, no class token, avg pool - * `vit_relpos_base_patch16_224` - 82.5 @ 224, 83.6 @ 320 -- rel pos, layer scale, no class token, avg pool - * `vit_base_patch16_rpn_224` - 82.3 @ 224 -- rel pos + res-post-norm, no class token, avg pool -* Vision Transformer refactor to remove representation layer that was only used in initial vit and rarely used since with newer pretrain (ie `How to Train Your ViT`) -* `vit_*` models support removal of class token, use of global average pool, use of fc_norm (ala beit, mae). - -### April 22, 2022 - -* `timm` models are now officially supported in [fast.ai](https://www.fast.ai/)! Just in time for the new Practical Deep Learning course. `timmdocs` documentation link updated to [timm.fast.ai](http://timm.fast.ai/). -* Two more model weights added in the TPU trained [series](https://github.com/rwightman/pytorch-image-models/releases/tag/v0.1-tpu-weights). Some In22k pretrain still in progress. - * `seresnext101d_32x8d` - 83.69 @ 224, 84.35 @ 288 - * `seresnextaa101d_32x8d` (anti-aliased w/ AvgPool2d) - 83.85 @ 224, 84.57 @ 288 - -### March 23, 2022 - -* Add `ParallelBlock` and `LayerScale` option to base vit models to support model configs in [Three things everyone should know about ViT](https://arxiv.org/abs/2203.09795) -* `convnext_tiny_hnf` (head norm first) weights trained with (close to) A2 recipe, 82.2% top-1, could do better with more epochs. - -### March 21, 2022 - -* Merge `norm_norm_norm`. **IMPORTANT** this update for a coming 0.6.x release will likely de-stabilize the master branch for a while. Branch [`0.5.x`](https://github.com/rwightman/pytorch-image-models/tree/0.5.x) or a previous 0.5.x release can be used if stability is required. -* Significant weights update (all TPU trained) as described in this [release](https://github.com/rwightman/pytorch-image-models/releases/tag/v0.1-tpu-weights) - * `regnety_040` - 82.3 @ 224, 82.96 @ 288 - * `regnety_064` - 83.0 @ 224, 83.65 @ 288 - * `regnety_080` - 83.17 @ 224, 83.86 @ 288 - * `regnetv_040` - 82.44 @ 224, 83.18 @ 288 (timm pre-act) - * `regnetv_064` - 83.1 @ 224, 83.71 @ 288 (timm pre-act) - * `regnetz_040` - 83.67 @ 256, 84.25 @ 320 - * `regnetz_040h` - 83.77 @ 256, 84.5 @ 320 (w/ extra fc in head) - * `resnetv2_50d_gn` - 80.8 @ 224, 81.96 @ 288 (pre-act GroupNorm) - * `resnetv2_50d_evos` 80.77 @ 224, 82.04 @ 288 (pre-act EvoNormS) - * `regnetz_c16_evos` - 81.9 @ 256, 82.64 @ 320 (EvoNormS) - * `regnetz_d8_evos` - 83.42 @ 256, 84.04 @ 320 (EvoNormS) - * `xception41p` - 82 @ 299 (timm pre-act) - * `xception65` - 83.17 @ 299 - * `xception65p` - 83.14 @ 299 (timm pre-act) - * `resnext101_64x4d` - 82.46 @ 224, 83.16 @ 288 - * `seresnext101_32x8d` - 83.57 @ 224, 84.270 @ 288 - * `resnetrs200` - 83.85 @ 256, 84.44 @ 320 -* HuggingFace hub support fixed w/ initial groundwork for allowing alternative 'config sources' for pretrained model definitions and weights (generic local file / remote url support soon) -* SwinTransformer-V2 implementation added. Submitted by [Christoph Reich](https://github.com/ChristophReich1996). Training experiments and model changes by myself are ongoing so expect compat breaks. -* Swin-S3 (AutoFormerV2) models / weights added from https://github.com/microsoft/Cream/tree/main/AutoFormerV2 -* MobileViT models w/ weights adapted from https://github.com/apple/ml-cvnets -* PoolFormer models w/ weights adapted from https://github.com/sail-sg/poolformer -* VOLO models w/ weights adapted from https://github.com/sail-sg/volo -* Significant work experimenting with non-BatchNorm norm layers such as EvoNorm, FilterResponseNorm, GroupNorm, etc -* Enhance support for alternate norm + act ('NormAct') layers added to a number of models, esp EfficientNet/MobileNetV3, RegNet, and aligned Xception -* Grouped conv support added to EfficientNet family -* Add 'group matching' API to all models to allow grouping model parameters for application of 'layer-wise' LR decay, lr scale added to LR scheduler -* Gradient checkpointing support added to many models -* `forward_head(x, pre_logits=False)` fn added to all models to allow separate calls of `forward_features` + `forward_head` -* All vision transformer and vision MLP models update to return non-pooled / non-token selected features from `foward_features`, for consistency with CNN models, token selection or pooling now applied in `forward_head` - -### Feb 2, 2022 - -* [Chris Hughes](https://github.com/Chris-hughes10) posted an exhaustive run through of `timm` on his blog yesterday. Well worth a read. [Getting Started with PyTorch Image Models (timm): A Practitioner’s Guide](https://towardsdatascience.com/getting-started-with-pytorch-image-models-timm-a-practitioners-guide-4e77b4bf9055) -* I'm currently prepping to merge the `norm_norm_norm` branch back to master (ver 0.6.x) in next week or so. - * The changes are more extensive than usual and may destabilize and break some model API use (aiming for full backwards compat). So, beware `pip install git+https://github.com/rwightman/pytorch-image-models` installs! - * `0.5.x` releases and a `0.5.x` branch will remain stable with a cherry pick or two until dust clears. Recommend sticking to pypi install for a bit if you want stable. - -### Jan 14, 2022 - -* Version 0.5.4 w/ release to be pushed to pypi. It's been a while since last pypi update and riskier changes will be merged to main branch soon.... -* Add ConvNeXT models /w weights from official impl (https://github.com/facebookresearch/ConvNeXt), a few perf tweaks, compatible with timm features -* Tried training a few small (~1.8-3M param) / mobile optimized models, a few are good so far, more on the way... - * `mnasnet_small` - 65.6 top-1 - * `mobilenetv2_050` - 65.9 - * `lcnet_100/075/050` - 72.1 / 68.8 / 63.1 - * `semnasnet_075` - 73 - * `fbnetv3_b/d/g` - 79.1 / 79.7 / 82.0 -* TinyNet models added by [rsomani95](https://github.com/rsomani95) -* LCNet added via MobileNetV3 architecture - -### Nov 22, 2021 - -* A number of updated weights anew new model defs - * `eca_halonext26ts` - 79.5 @ 256 - * `resnet50_gn` (new) - 80.1 @ 224, 81.3 @ 288 - * `resnet50` - 80.7 @ 224, 80.9 @ 288 (trained at 176, not replacing current a1 weights as default since these don't scale as well to higher res, [weights](https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rsb-weights/resnet50_a1h2_176-001a1197.pth)) - * `resnext50_32x4d` - 81.1 @ 224, 82.0 @ 288 - * `sebotnet33ts_256` (new) - 81.2 @ 224 - * `lamhalobotnet50ts_256` - 81.5 @ 256 - * `halonet50ts` - 81.7 @ 256 - * `halo2botnet50ts_256` - 82.0 @ 256 - * `resnet101` - 82.0 @ 224, 82.8 @ 288 - * `resnetv2_101` (new) - 82.1 @ 224, 83.0 @ 288 - * `resnet152` - 82.8 @ 224, 83.5 @ 288 - * `regnetz_d8` (new) - 83.5 @ 256, 84.0 @ 320 - * `regnetz_e8` (new) - 84.5 @ 256, 85.0 @ 320 -* `vit_base_patch8_224` (85.8 top-1) & `in21k` variant weights added thanks [Martins Bruveris](https://github.com/martinsbruveris) -* Groundwork in for FX feature extraction thanks to [Alexander Soare](https://github.com/alexander-soare) - * models updated for tracing compatibility (almost full support with some distlled transformer exceptions) - -### Oct 19, 2021 - -* ResNet strikes back (https://arxiv.org/abs/2110.00476) weights added, plus any extra training components used. Model weights and some more details here (https://github.com/rwightman/pytorch-image-models/releases/tag/v0.1-rsb-weights) -* BCE loss and Repeated Augmentation support for RSB paper -* 4 series of ResNet based attention model experiments being added (implemented across byobnet.py/byoanet.py). These include all sorts of attention, from channel attn like SE, ECA to 2D QKV self-attention layers such as Halo, Bottlneck, Lambda. Details here (https://github.com/rwightman/pytorch-image-models/releases/tag/v0.1-attn-weights) -* Working implementations of the following 2D self-attention modules (likely to be differences from paper or eventual official impl): - * Halo (https://arxiv.org/abs/2103.12731) - * Bottleneck Transformer (https://arxiv.org/abs/2101.11605) - * LambdaNetworks (https://arxiv.org/abs/2102.08602) -* A RegNetZ series of models with some attention experiments (being added to). These do not follow the paper (https://arxiv.org/abs/2103.06877) in any way other than block architecture, details of official models are not available. See more here (https://github.com/rwightman/pytorch-image-models/releases/tag/v0.1-attn-weights) -* ConvMixer (https://openreview.net/forum?id=TVHS5Y4dNvM), CrossVit (https://arxiv.org/abs/2103.14899), and BeiT (https://arxiv.org/abs/2106.08254) architectures + weights added -* freeze/unfreeze helpers by [Alexander Soare](https://github.com/alexander-soare) - -### Aug 18, 2021 - -* Optimizer bonanza! - * Add LAMB and LARS optimizers, incl trust ratio clipping options. Tweaked to work properly in PyTorch XLA (tested on TPUs w/ `timm bits` [branch](https://github.com/rwightman/pytorch-image-models/tree/bits_and_tpu/timm/bits)) - * Add MADGRAD from FB research w/ a few tweaks (decoupled decay option, step handling that works with PyTorch XLA) - * Some cleanup on all optimizers and factory. No more `.data`, a bit more consistency, unit tests for all! - * SGDP and AdamP still won't work with PyTorch XLA but others should (have yet to test Adabelief, Adafactor, Adahessian myself). -* EfficientNet-V2 XL TF ported weights added, but they don't validate well in PyTorch (L is better). The pre-processing for the V2 TF training is a bit diff and the fine-tuned 21k -> 1k weights are very sensitive and less robust than the 1k weights. -* Added PyTorch trained EfficientNet-V2 'Tiny' w/ GlobalContext attn weights. Only .1-.2 top-1 better than the SE so more of a curiosity for those interested. diff --git a/hfdocs/source/training_hparam_examples.mdx b/hfdocs/source/training_hparam_examples.mdx deleted file mode 100644 index e582cfc916..0000000000 --- a/hfdocs/source/training_hparam_examples.mdx +++ /dev/null @@ -1,63 +0,0 @@ -# Training Examples - -## EfficientNet-B2 with RandAugment - 80.4 top-1, 95.1 top-5 - -These params are for dual Titan RTX cards with NVIDIA Apex installed: - -```bash -./distributed_train.sh 2 /imagenet/ --model efficientnet_b2 -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .016 -``` - -## MixNet-XL with RandAugment - 80.5 top-1, 94.9 top-5 - -This params are for dual Titan RTX cards with NVIDIA Apex installed: - -```bash -./distributed_train.sh 2 /imagenet/ --model mixnet_xl -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .969 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.3 --amp --lr .016 --dist-bn reduce -``` - -## SE-ResNeXt-26-D and SE-ResNeXt-26-T - -These hparams (or similar) work well for a wide range of ResNet architecture, generally a good idea to increase the epoch # as the model size increases... ie approx 180-200 for ResNe(X)t50, and 220+ for larger. Increase batch size and LR proportionally for better GPUs or with AMP enabled. These params were for 2 1080Ti cards: - -```bash -./distributed_train.sh 2 /imagenet/ --model seresnext26t_32x4d --lr 0.1 --warmup-epochs 5 --epochs 160 --weight-decay 1e-4 --sched cosine --reprob 0.4 --remode pixel -b 112 -``` -## EfficientNet-B3 with RandAugment - 81.5 top-1, 95.7 top-5 - -The training of this model started with the same command line as EfficientNet-B2 w/ RA above. After almost three weeks of training the process crashed. The results weren't looking amazing so I resumed the training several times with tweaks to a few params (increase RE prob, decrease rand-aug, increase ema-decay). Nothing looked great. I ended up averaging the best checkpoints from all restarts. The result is mediocre at default res/crop but oddly performs much better with a full image test crop of 1.0. - -## EfficientNet-B0 with RandAugment - 77.7 top-1, 95.3 top-5 - -[Michael Klachko](https://github.com/michaelklachko) achieved these results with the command line for B2 adapted for larger batch size, with the recommended B0 dropout rate of 0.2. - -```bash -./distributed_train.sh 2 /imagenet/ --model efficientnet_b0 -b 384 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .048 -``` -## ResNet50 with JSD loss and RandAugment (clean + 2x RA augs) - 79.04 top-1, 94.39 top-5 - -Trained on two older 1080Ti cards, this took a while. Only slightly, non statistically better ImageNet validation result than my first good AugMix training of 78.99. However, these weights are more robust on tests with ImageNetV2, ImageNet-Sketch, etc. Unlike my first AugMix runs, I've enabled SplitBatchNorm, disabled random erasing on the clean split, and cranked up random erasing prob on the 2 augmented paths. - -```bash -./distributed_train.sh 2 /imagenet -b 64 --model resnet50 --sched cosine --epochs 200 --lr 0.05 --amp --remode pixel --reprob 0.6 --aug-splits 3 --aa rand-m9-mstd0.5-inc1 --resplit --split-bn --jsd --dist-bn reduce -``` -## EfficientNet-ES (EdgeTPU-Small) with RandAugment - 78.066 top-1, 93.926 top-5 - -Trained by [Andrew Lavin](https://github.com/andravin) with 8 V100 cards. Model EMA was not used, final checkpoint is the average of 8 best checkpoints during training. - -```bash -./distributed_train.sh 8 /imagenet --model efficientnet_es -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .064 -``` -## MobileNetV3-Large-100 - 75.766 top-1, 92,542 top-5 - -```bash -./distributed_train.sh 2 /imagenet/ --model mobilenetv3_large_100 -b 512 --sched step --epochs 600 --decay-epochs 2.4 --decay-rate .973 --opt rmsproptf --opt-eps .001 -j 7 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .064 --lr-noise 0.42 0.9 -``` - -## ResNeXt-50 32x4d w/ RandAugment - 79.762 top-1, 94.60 top-5 -These params will also work well for SE-ResNeXt-50 and SK-ResNeXt-50 and likely 101. I used them for the SK-ResNeXt-50 32x4d that I trained with 2 GPU using a slightly higher LR per effective batch size (lr=0.18, b=192 per GPU). The cmd line below are tuned for 8 GPU training. - - -```bash -./distributed_train.sh 8 /imagenet --model resnext50_32x4d --lr 0.6 --warmup-epochs 5 --epochs 240 --weight-decay 1e-4 --sched cosine --reprob 0.4 --recount 3 --remode pixel --aa rand-m7-mstd0.5-inc1 -b 192 -j 6 --amp --dist-bn reduce -``` From 13b73682a5737d5874bf1997086cb24e5de70bc4 Mon Sep 17 00:00:00 2001 From: nateraw Date: Tue, 13 Dec 2022 13:57:27 -0500 Subject: [PATCH 28/35] :memo: update index doc --- hfdocs/source/index.mdx | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/hfdocs/source/index.mdx b/hfdocs/source/index.mdx index 0a9f08a19e..e6b43ec7c9 100644 --- a/hfdocs/source/index.mdx +++ b/hfdocs/source/index.mdx @@ -1,7 +1,22 @@ # timm + + `timm` is a library containing SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations, and training/evaluation scripts. It comes packaged with >100 pretrained models, and is designed to be flexible and easy to use. Read the [quick start guide](quickstart) to get up and running with the `timm` library. You will learn how to load, discover, and use pretrained models included in the library. + +
+
+
Tutorials
+

Learn the basics and become familiar with timm. Start here if you are using timm for the first time!

+ +
Reference
+

Technical descriptions of how timm classes and methods work.

+ +
+
From caa54d4a13cceba1f90f6a3d7cece8a7d492d026 Mon Sep 17 00:00:00 2001 From: nateraw Date: Tue, 13 Dec 2022 14:12:13 -0500 Subject: [PATCH 29/35] :memo: update number of pretrained models --- hfdocs/source/index.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hfdocs/source/index.mdx b/hfdocs/source/index.mdx index e6b43ec7c9..cffa569399 100644 --- a/hfdocs/source/index.mdx +++ b/hfdocs/source/index.mdx @@ -4,7 +4,7 @@ `timm` is a library containing SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations, and training/evaluation scripts. -It comes packaged with >100 pretrained models, and is designed to be flexible and easy to use. +It comes packaged with >700 pretrained models, and is designed to be flexible and easy to use. Read the [quick start guide](quickstart) to get up and running with the `timm` library. You will learn how to load, discover, and use pretrained models included in the library. From 03789e46bacd1c0f63fa7dfb26a0bebba33987e2 Mon Sep 17 00:00:00 2001 From: Nathan Raw Date: Wed, 14 Dec 2022 21:34:08 -0500 Subject: [PATCH 30/35] Update hfdocs/README.md --- hfdocs/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hfdocs/README.md b/hfdocs/README.md index f8819c4931..a0178812d4 100644 --- a/hfdocs/README.md +++ b/hfdocs/README.md @@ -10,5 +10,5 @@ pip install watchdog black ## Preview the Docs Locally ``` -doc-builder preview pytorch-image-models hfdocs/source --not_python_module +doc-builder preview timm hfdocs/source ``` From 00f3dd1e1505b89b8fd407effe3a3a7346ca8d54 Mon Sep 17 00:00:00 2001 From: Nathan Raw Date: Wed, 14 Dec 2022 21:41:51 -0500 Subject: [PATCH 31/35] Update .github/workflows/build_pr_documentation.yml --- .github/workflows/build_pr_documentation.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index 934a7acdd4..6647be72c6 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -9,6 +9,7 @@ concurrency: jobs: build: + # TODO - switch back to main branch before merging uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@repo-owner-bugfix with: commit_sha: ${{ github.event.pull_request.head.sha }} From 217409e6eda9305ea14574bacbbf0def532a178b Mon Sep 17 00:00:00 2001 From: Nathan Raw Date: Thu, 15 Dec 2022 15:19:29 -0500 Subject: [PATCH 32/35] Update build_pr_documentation.yml --- .github/workflows/build_pr_documentation.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index 6647be72c6..910817d5b1 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -18,3 +18,4 @@ jobs: package_name: timm repo_owner: rwightman path_to_docs: pytorch-image-models/hfdocs/source + version_tag_suffix: "" From 45e4247c2de96730785d22972a167103151249f6 Mon Sep 17 00:00:00 2001 From: Nathan Raw Date: Thu, 15 Dec 2022 15:36:02 -0500 Subject: [PATCH 33/35] bump From bb88e1f6166971d6a2152638797926f45a818369 Mon Sep 17 00:00:00 2001 From: nateraw Date: Tue, 3 Jan 2023 10:24:07 -0500 Subject: [PATCH 34/35] :pushpin: update gh action to use main branch --- .github/workflows/build_pr_documentation.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index 910817d5b1..f6f96a0ff9 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -10,7 +10,7 @@ concurrency: jobs: build: # TODO - switch back to main branch before merging - uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@repo-owner-bugfix + uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main with: commit_sha: ${{ github.event.pull_request.head.sha }} pr_number: ${{ github.event.number }} From 35d5241ec75d699e587f30c29c073d68ddf1c655 Mon Sep 17 00:00:00 2001 From: nateraw Date: Tue, 3 Jan 2023 10:32:21 -0500 Subject: [PATCH 35/35] :fire: remove comment --- .github/workflows/build_pr_documentation.yml | 1 - 1 file changed, 1 deletion(-) diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index f6f96a0ff9..2b44619f69 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -9,7 +9,6 @@ concurrency: jobs: build: - # TODO - switch back to main branch before merging uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main with: commit_sha: ${{ github.event.pull_request.head.sha }}