Unofficial PyTorch implementation of RegNet based on paper Designing Network Design Spaces.
General network structure X block based on the standard residual bottleneck block with group convolution
Top RegNetX Models Top RegNetY Models
- Single node with one GPU
python main.py
- Single node with multi GPU
CUDA_VISIBLE_DEVICES=3,4 python -m torch.distributed.launch --nproc_per_node=2 --master_port=6666 main_ddp.py
optional arguments:
-h, --help show this help message and exit
--gpu_device GPU_DEVICE
Select specific GPU to run the model
--batch-size N Input batch size for training (default: 64)
--epochs N Number of epochs to train (default: 20)
--num-class N Number of classes to classify (default: 10)
--lr LR Learning rate (default: 0.01)
--weight-decay WD Weight decay (default: 1e-5)
--model-path PATH Path to save the model
Model | params(M) | batch size | epochs | train(hr) | Acc@1 | Acc@5 |
---|---|---|---|---|---|---|
REGNETY-400MF | 4.4 | 256 | 90 | 39 | 71.522% | 90.146% |
@InProceedings{Radosavovic2020,
title = {Designing Network Design Spaces},
author = {Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Doll{\'a}r},
booktitle = {CVPR},
year = {2020}
}