thomasverelst/dynconv
Code for Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference (CVPR2020)
Cuda
Issues
- 0
- 0
发生异常: RuntimeError CUDA error: the launch timed out and was terminated File "/home/lym/Compare experiment new/classification/main_cifar.py", line 72, in main model = net_module(sparse=args.budget >= 0, pretrained=args.pretrained).to(device=device) File "/home/lym/Compare experiment new/classification/main_cifar.py", line 232, in <module> main()
#14 opened by liuyiming199721 - 0
Questions about mask usage in convolution
#13 opened by antao97 - 2
Questions about mask generation
#12 opened by magehrig - 1
About pose environment
#11 opened by CheungBH - 2
question about the sparsity_target
#10 opened by albertszg - 3
- 3
/annot/valid.json is missing
#8 opened by zhang-pengyu - 1
Training on Google Colab
#7 opened by fbagci - 0
Ponder_Cost_Plotting
#6 opened by rida-rida - 2
- 2
- 6
Mask calculation
#3 opened by qiulinzhang - 5
About multi-gpu training
#2 opened by d-li14 - 2
A question about soft-mask calculation
#1 opened by peter943