Issues
- 12
Target prune FLOPs ratio
#4 opened by King4819 - 2
- 2
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [3]], which is output 0 of CumprodBackward0, is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
#1 opened by railgun-zyy - 14
How to prune own models
#2 opened by mskmei