@inproceedings{
cai2020once,
title={Once for All: Train One Network and Specialize it for Efficient Deployment},
author={Han Cai and Chuang Gan and Tianzhe Wang and Zhekai Zhang and Song Han},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://arxiv.org/pdf/1908.09791.pdf}
}[News] The hands-on tutorial of OFA is released!
[News] OFA is available via pip! Run pip install ofa to install the whole OFA codebase.
[News] Fisrt place in the 4th Low-Power Computer Vision Challenge, both classification and detection track.
[News] First place in the 3rd Low-Power Computer Vision Challenge, DSP track at ICCV’19 using the Once-for-all Network.
""" OFA Specialized Networks.
Example: net, image_size = ofa_specialized('flops@[email protected]_finetune@75', pretrained=True)
"""
from ofa.model_zoo import ofa_specialized
net, image_size = ofa_specialized(net_id, pretrained=True)If the above scripts failed to download, you download it manually from Google Drive and put them under $HOME/.torch/ofa_specialized/.
python eval_specialized_net.py --path 'Your path to imagent' --net flops@[email protected]_finetune@75
- flops@[email protected]_finetune@75
- flops@[email protected]_finetune@75
- flops@[email protected]_finetune@75
|
LG G8
|
Samsung Note8
|
|
Google Pixel1
|
Samsung Note10
|
|
Google Pixel2
|
Samsung S7 Edge
|
|
1080ti GPU (Batch Size 64)
|
V100 GPU (Batch Size 64)
|
|
Jetson TX2 GPU (Batch Size 16)
|
Intel Xeon CPU with MKL-DNN (Batch Size 1)
|
""" OFA Networks.
Example: ofa_network = ofa_net('ofa_mbv3_d234_e346_k357_w1.0', pretrained=True)
"""
from ofa.model_zoo import ofa_net
ofa_network = ofa_net(net_id, pretrained=True)
# Randomly sample sub-networks from OFA network
ofa_network.sample_active_subnet()
random_subnet = ofa_network.get_active_subnet(preserve_weight=True)
# Manually set the sub-network
ofa_network.set_active_subnet(ks=7, e=6, d=4)
manual_subnet = ofa_network.get_active_subnet(preserve_weight=True)If the above scripts failed to download, you download it manually from Google Drive and put them under $HOME/.torch/ofa_nets/.
python eval_ofa_net.py --path 'Your path to imagenet' --net ofa_mbv3_d234_e346_k357_w1.0
mpirun -np 32 -H <server1_ip>:8,<server2_ip>:8,<server3_ip>:8,<server4_ip>:8 \
-bind-to none -map-by slot \
-x NCCL_DEBUG=INFO -x LD_LIBRARY_PATH -x PATH \
python train_ofa_net.pyor
horovodrun -np 32 -H <server1_ip>:8,<server2_ip>:8,<server3_ip>:8,<server4_ip>:8 \
python train_ofa_net.py
- Python 3.6
- Pytorch 1.0.0
- ImageNet Dataset
- Horovod
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware (ICLR’19)
AutoML for Architecting Efficient and Specialized Neural Networks (IEEE Micro)
AMC: AutoML for Model Compression and Acceleration on Mobile Devices (ECCV’18)
HAQ: Hardware-Aware Automated Quantization (CVPR’19, oral)