This pull request includes several important updates and fixes to ensure compatibility with the latest version of PyTorch and to resolve issues related to tensor operations while training AlexNet on the CIFAR dataset.
The key changes are as follows:
Removed async=True argument from cuda() calls: This argument is deprecated in PyTorch 1.0.0 and has been removed to maintain compatibility.
Commit: 5c70d06
Refactored code to use torch.no_grad() instead of volatile=True: Updated to the new context manager approach to handle operations without tracking gradients for better efficiency with the latest PyTorch version.
Commit: 4d393ff
Fixed tensor reshaping in the accuracy function: Replaced view with reshape to correct issues when reshaping tensors, improving reliability.
Commit: d378d87
Addressed all 0-dim tensor indexing errors in cifar.py: Accessing 0-dim tensors caused index errors, ensuring smooth operation during training and metrics update.
Commits: c570bd6, 2935578
Additional Information:
Files Changed:
cifar.py: Updated to remove deprecated or obsolete arguments and fix tensor operations
eval.py: Adjusted tensor reshaping logic for accuracy calculation
This pull request includes several important updates and fixes to ensure compatibility with the latest version of PyTorch and to resolve issues related to tensor operations while training AlexNet on the CIFAR dataset.
The key changes are as follows:
Removed
async=Trueargument fromcuda()calls: This argument is deprecated in PyTorch 1.0.0 and has been removed to maintain compatibility.5c70d06Refactored code to use
torch.no_grad()instead ofvolatile=True: Updated to the new context manager approach to handle operations without tracking gradients for better efficiency with the latest PyTorch version.4d393ffFixed tensor reshaping in the accuracy function: Replaced
viewwithreshapeto correct issues when reshaping tensors, improving reliability.d378d87Addressed all 0-dim tensor indexing errors in cifar.py: Accessing 0-dim tensors caused index errors, ensuring smooth operation during training and metrics update.
c570bd6,2935578Additional Information: