Releases: sony/nnabla-nas
Version 0.15.0 Release
NNabla NAS version 0.15.0
We are delighted to announce the release NNabla NAS, the Neural Architecture Search framework for NNabla.
We hope that this new member of the NNabla ecosystem will help you to design and develop
Neural Networks for you applications and products in an easy and efficient way.
We are actively developing NNabla NAS, improving its usability, adding latest research methods and expanding its range of applications.
To improve NNabla NAS, we welcome your feedback and on your contributions to the project.
release-note-bugfix
- Bugfix for loading dataloder of OFA reset_bn_statistics
- Fix ImageNet data file directory
- Fix Dynamic BN for inefficient memory use
- Fix bz parameter for schedulers
release-note-core
release-note-doc
- Fix readthedocs dependency for version switch issue
- Add .readthedocs.yaml v2
- Add the API information of OFASearcher and OFA-based search spaces to docs
Key Features
Search Space
- Flexible way to define search spaces
- Efficient sampling of architectures from search space (fast)
- Predefined top level modules to define candidate architectures (e.g. inverted residual blocks, drop path, dilated depthwise separable, factorized reduction layer, etc.)
Search Algorithms
- Searcher algorithms to learn the architecture and model parameters (e.g., DartsSearcher and ProxylessNasSearcher)
Hardware constraint
A key feature of NNabla NAS is the ability to search architectures with hardware constraint.
- Can be used to enforce hardware constraints (e.g. LatencyEstimator and MemoryEstimator)
- NNabla NAS implements online latency profilers for CPU and GPU and offline profiling for other devices (getting latency from look-up table)
Other Features
- Logging and visualization based on the tensorboard (https://www.tensorflow.org/tensorboard/get_started)
- Graph visualization of networks and search spaces
- Multi-GPU Support
- Image Augmentation with NVIDIA DALI (https://developer.nvidia.com/DALI)
Quick Start
Install
First you need to install NNabla with the configuration that suit your environment. Follow the instruction from https://nnabla.org/install/ . E.g, if you have cuda 11.0:
pip install -U nnabla-ext-cuda110
If you want to use dataloader.imagenet you have to install nvidia-dali
pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/ nvidia-dali-cuda110
You need to install graphviz to visualize NAS results.
apt install graphviz
To install NNabla NAS, simply run the following pip install in an environment with python >= 3.7
pip install -U nnabla-nas
Version 0.14.0 Release
NNabla NAS version 0.14.0
We are delighted to announce the release NNabla NAS, the Neural Architecture Search framework for NNabla.
We hope that this new member of the NNabla ecosystem will help you to design and develop
Neural Networks for you applications and products in an easy and efficient way.
We are actively developing NNabla NAS, improving its usability, adding latest research methods and expanding its range of applications.
To improve NNabla NAS, we welcome your feedback and on your contributions to the project.
release-note-bugfix
- Fix wrong path to working directory when saving and loading files
- Remove the duplicate processes of saving learned weights in OFA searcher
- Fix KeyError: 'comm'.
- [OFA] Add loss_weights arg in configs
- Fix OFA valid/test
- Fix imagenet datapath
- Fix wrong working directory for OFAResnet50 and OFAXception search spaces
release-note-build
release-note-core
Key Features
Search Space
- Flexible way to define search spaces
- Efficient sampling of architectures from search space (fast)
- Predefined top level modules to define candidate architectures (e.g. inverted residual blocks, drop path, dilated depthwise separable, factorized reduction layer, etc.)
Search Algorithms
- Searcher algorithms to learn the architecture and model parameters (e.g., DartsSearcher and ProxylessNasSearcher)
Hardware constraint
A key feature of NNabla NAS is the ability to search architectures with hardware constraint.
- Can be used to enforce hardware constraints (e.g. LatencyEstimator and MemoryEstimator)
- NNabla NAS implements online latency profilers for CPU and GPU and offline profiling for other devices (getting latency from look-up table)
Other Features
- Logging and visualization based on the tensorboard (https://www.tensorflow.org/tensorboard/get_started)
- Graph visualization of networks and search spaces
- Multi-GPU Support
- Image Augmentation with NVIDIA DALI (https://developer.nvidia.com/DALI)
Quick Start
Install
First you need to install NNabla with the configuration that suit your environment. Follow the instruction from https://nnabla.org/install/ . E.g, if you have cuda 11.0:
pip install -U nnabla-ext-cuda110
If you want to use dataloader.imagenet you have to install nvidia-dali
pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/ nvidia-dali-cuda110
You need to install graphviz to visualize NAS results.
apt install graphviz
To install NNabla NAS, simply run the following pip install in an environment with python >= 3.7
pip install -U nnabla-nas
Version 0.13.0 Release
NNabla NAS version 0.13.0
We are delighted to announce the release NNabla NAS, the Neural Architecture Search framework for NNabla.
We hope that this new member of the NNabla ecosystem will help you to design and develop
Neural Networks for you applications and products in an easy and efficient way.
We are actively developing NNabla NAS, improving its usability, adding latest research methods and expanding its range of applications.
To improve NNabla NAS, we welcome your feedback and on your contributions to the project.
release-note-bugfix
- Fix mismatching order of params of AvgPool
- f-string compatibility with Python version < 3.8
- Update imagenet.yaml
- Fixed jobs.sh
- Fixed OFA searcher to get correct net parameters with keys
- Fix parameters not being inherited.
- Bug fixes and refactoring of OFA utilities
- Add proper extra_repr to all OFA modules.
- Bug fixes of OFA DynamicBN layer
- Fixed missing regularizer arguments
- Bug fixes of OFA(Once-for-All) and add tutorials for OFA
release-note-build
release-note-core
- Add OFA-ResNet50
- Add OFA-Xception search space
- Implementation of mixed operations fast mode
- Support nnabla.no_grad etc.
- Extract elastic-nn-related codes to common packages for better code reuse
- Get regulizers out of the optimizers dictionary.
- Add the functions to save checkpoint and restart from it
release-note-doc
- Updated docs, readme and tutorials and gave timestamps to the config logs
- [OFA] Update Model Zoo README with results on imagenet
release-note-utility
- Switch to hydra to handle configurations
- Enable save nnp function for OFA searcher
- Update DALI Pipeline to the latest version for the ImageNet dataset
- add no_image_normalization param in executor when saving nnp
- add image augmentation for csv dataloader
- save arch.json when save-nnp option is specified.
Key Features
Search Space
- Flexible way to define search spaces
- Efficient sampling of architectures from search space (fast)
- Predefined top level modules to define candidate architectures (e.g. inverted residual blocks, drop path, dilated depthwise separable, factorized reduction layer, etc.)
Search Algorithms
- Searcher algorithms to learn the architecture and model parameters (e.g., DartsSearcher and ProxylessNasSearcher)
Hardware constraint
A key feature of NNabla NAS is the ability to search architectures with hardware constraint.
- Can be used to enforce hardware constraints (e.g. LatencyEstimator and MemoryEstimator)
- NNabla NAS implements online latency profilers for CPU and GPU and offline profiling for other devices (getting latency from look-up table)
Other Features
- Logging and visualization based on the tensorboard (https://www.tensorflow.org/tensorboard/get_started)
- Graph visualization of networks and search spaces
- Multi-GPU Support
- Image Augmentation with NVIDIA DALI (https://developer.nvidia.com/DALI)
Quick Start
Install
First you need to install NNabla with the configuration that suit your environment. Follow the instruction from https://nnabla.org/install/ . E.g, if you have cuda 11.0:
pip install -U nnabla-ext-cuda110
If you want to use dataloader.imagenet you have to install nvidia-dali
pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/ nvidia-dali-cuda110
You need to install graphviz to visualize NAS results.
apt install graphviz
To install NNabla NAS, simply run the following pip install in an environment with python >= 3.7
pip install -U nnabla-nas
Version 0.12.0 Release
NNabla NAS version 0.12.0
We are delighted to announce the release NNabla NAS, the Neural Architecture Search framework for NNabla.
We hope that this new member of the NNabla ecosystem will help you to design and develop
Neural Networks for you applications and products in an easy and efficient way.
We are actively developing NNabla NAS, improving its usability, adding latest research methods and expanding its range of applications.
To improve NNabla NAS, we welcome your feedback and on your contributions to the project.
release-note-bugfix
release-note-build
release-note-core
- Feature/20220127 ofa
- FairNAS implementation
- latency measurements and exporter functions to nnp and onnx
release-note-utility
Key Features
Search Space
- Flexible way to define search spaces
- Efficient sampling of architectures from search space (fast)
- Predefined top level modules to define candidate architectures (e.g. inverted residual blocks, drop path, dilated depthwise separable, factorized reduction layer, etc.)
Search Algorithms
- Searcher algorithms to learn the architecture and model parameters (e.g., DartsSearcher and ProxylessNasSearcher)
Hardware constraint
A key feature of NNabla NAS is the ability to search architectures with hardware constraint.
- Can be used to enforce hardware constraints (e.g. LatencyEstimator and MemoryEstimator)
- NNabla NAS implements online latency profilers for CPU and GPU and offline profiling for other devices (getting latency from look-up table)
Other Features
- Logging and visualization based on the tensorboard (https://www.tensorflow.org/tensorboard/get_started)
- Graph visualization of networks and search spaces
- Multi-GPU Support
- Image Augmentation with NVIDIA DALI (https://developer.nvidia.com/DALI)
Quick Start
Install
First you need to install NNabla with the configuration that suit your environment. Follow the instruction from https://nnabla.org/download/ . E.g, if you have cuda 10.2:
pip install -U nnabla-ext-cuda102
If you want to use dataloader.imagenet you have to install nvidia-dali
pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/ nvidia-dali-cuda100
You need to install graphviz to visualize NAS results.
apt install graphviz
To install NNabla NAS, simply run the following pip install in an environment with python >= 3.7
pip install -U nnabla-nas
Version 0.11.0 Release
NNabla NAS version 0.11.0
We are delighted to announce the release NNabla NAS, the Neural Architecture Search framework for NNabla.
We hope that this new member of the NNabla ecosystem will help you to design and develop
Neural Networks for you applications and products in an easy and efficient way.
We are actively developing NNabla NAS, improving its usability, adding latest research methods and expanding its range of applications.
To improve NNabla NAS, we welcome your feedback and on your contributions to the project.
Fix
- [Fix URLs in documentations] (#5)
Key Features
Search Space
- Flexible way to define search spaces
- Efficient sampling of architectures from search space (fast)
- Predefined top level modules to define candidate architectures (e.g. inverted residual blocks, drop path, dilated depthwise separable, factorized reduction layer, etc.)
Search Algorithms
- Searcher algorithms to learn the architecture and model parameters (e.g., DartsSearcher and ProxylessNasSearcher)
Hardware constraint
A key feature of NNabla NAS is the ability to search architectures with hardware constraint.
- Can be used to enforce hardware constraints (e.g. LatencyEstimator and MemoryEstimator)
- NNabla NAS implements online latency profilers for CPU and GPU and offline profiling for other devices (getting latency from look-up table)
Other Features
- Logging and visualization based on the tensorboard (https://www.tensorflow.org/tensorboard/get_started)
- Graph visualization of networks and search spaces
- Multi-GPU Support
- Image Augmentation with NVIDIA DALI (https://developer.nvidia.com/DALI)
Quick Start
Install
First you need to install NNabla with the configuration that suit your environment. Follow the instruction from https://nnabla.org/download/ . E.g, if you have cuda 10.2:
pip install -U nnabla-ext-cuda102
If you want to use dataloader.imagenet you have to install nvidia-dali
pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/ nvidia-dali-cuda100
You need to install graphviz to visualize NAS results.
apt install graphviz
To install NNabla NAS, simply run the following pip install in an environment with python >= 3.6
pip install -U nnabla-nas
Version 0.10.0 Release
NNabla NAS version 0.10.0
We are delighted to announce the release NNabla NAS, the Neural Architecture Search framework for NNabla.
We hope that this new member of the NNabla ecosystem will help you to design and develop
Neural Networks for you applications and products in an easy and efficient way.
We are actively developing NNabla NAS, improving its usability, adding latest research methods and expanding its range of applications.
To improve NNabla NAS, we welcome your feedback and on your contributions to the project.
enhancement
bug-fix
Key Features
Search Space
- Flexible way to define search spaces
- Efficient sampling of architectures from search space (fast)
- Predefined top level modules to define candidate architectures (e.g. inverted residual blocks, drop path, dilated depthwise separable, factorized reduction layer, etc.)
Search Algorithms
- Searcher algorithms to learn the architecture and model parameters (e.g., DartsSearcher and ProxylessNasSearcher)
Hardware constraint
A key feature of NNabla NAS is the ability to search architectures with hardware constraint.
- Can be used to enforce hardware constraints (e.g. LatencyEstimator and MemoryEstimator)
- NNabla NAS implements online latency profilers for CPU and GPU and offline profiling for other devices (getting latency from look-up table)
Other Features
- Logging and visualization based on the tensorboard (https://www.tensorflow.org/tensorboard/get_started)
- Graph visualization of networks and search spaces
- Multi-GPU Support
- Image Augmentation with NVIDIA DALI (https://developer.nvidia.com/DALI)
Quick Start
Install
First you need to install NNabla with the configuration that suit your environment. Follow the instruction from https://nnabla.org/download/ . E.g, if you have cuda 10.2:
pip install -U nnabla-ext-cuda102
If you want to use dataloader.imagenet you have to install nvidia-dali
pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/ nvidia-dali-cuda100
You need to install graphviz to visualize NAS results.
apt install graphviz
To install NNabla NAS, simply run the following pip install in an environment with python >= 3.6
pip install -U nnabla-nas
Version 0.9.0 release
NNabla NAS version 0.9.0
We are delighted to announce the release NNabla NAS, the Neural Architecture Search framework for NNabla.
We hope that this new member of the NNabla ecosystem will help you to design and develop
Neural Networks for you applications and products in an easy and efficient way.
We are actively developing NNabla NAS, improving its usability, adding latest research methods and expanding its range of applications.
To improve NNabla NAS, we welcome your feedback and on your contributions to the project.
Key Features
Search Space
- Flexible way to define search spaces
- Efficient sampling of architectures from search space (fast)
- Predefined top level modules to define candidate architectures (e.g. inverted residual blocks, drop path, dilated depthwise separable, factorized reduction layer, etc.)
Search Algorithms
- Searcher algorithms to learn the architecture and model parameters (e.g.,
DartsSearcherandProxylessNasSearcher)
Hardware constraint
A key feature of NNabla NAS is the ability to search architectures with hardware constraint.
- Can be used to enforce hardware constraints (e.g.
LatencyEstimatorandMemoryEstimator) - NNabla NAS implements online latency profilers for CPU and GPU and offline profiling for other devices (getting latency from look-up table)
Other Features
- Logging and visualization based on the tensorboard (https://www.tensorflow.org/tensorboard/get_started)
- Graph visualization of networks and search spaces
- Multi-GPU Support
- Image Augmentation with NVIDIA DALI (https://developer.nvidia.com/DALI)
Quick Start
Install
First you need to install NNabla with the configuration that suit your environment. Follow the instruction from https://nnabla.org/download/ . E.g, if you have cuda 10.2:
pip install -U nnabla-ext-cuda102
If you want to use dataloader.imagenet you have to install nvidia-dali
pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/ nvidia-dali-cuda100
You need to install graphviz to visualize NAS results.
apt install graphviz
To install NNabla NAS, simply run the following pip install in an environment with python >= 3.6
pip install -U nnabla-nas