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