facebookresearch/d2go
D2Go is a toolkit for efficient deep learning
| repo name | facebookresearch/d2go |
| repo link | https://github.com/facebookresearch/d2go |
| homepage | |
| language | Python |
| size (curr.) | 1249 kB |
| stars (curr.) | 421 |
| created | 2021-02-12 |
| license | Apache License 2.0 |
D2Go
D2Go is a production ready software system from FacebookResearch, which supports end-to-end model training and deployment for mobile platforms.
What’s D2Go
- It is a deep learning toolkit powered by PyTorch and Detectron2.
- State-of-the-art efficient backbone networks for mobile devices.
- End-to-end model training, quantization and deployment pipeline.
- Easy export to TorchScript format for deployment.
Installation
Install PyTorch Nightly (use CUDA 10.2 as example, see details at PyTorch Website):
conda install pytorch torchvision cudatoolkit=10.2 -c pytorch-nightly
Install Detectron2 (other installation options at Detectron2):
python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'
Install mobile_cv:
python -m pip install 'git+https://github.com/facebookresearch/mobile-vision.git'
Install d2go:
git clone https://github.com/facebookresearch/d2go
cd d2go & python -m pip install .
Get Started
-
See our model zoo for example configs and pretrained models.
License
D2Go is released under the Apache 2.0 license.
