Fix CUDA/CPU tensor mismatch in image classifier prediction#679
Open
Irozuku wants to merge 1 commit into
Open
Conversation
Loaded checkpoints rebuild the backbone on CPU, but predict moved only the input images to the device, causing a CUDA/CPU tensor type mismatch. Move the model to the device before inference in all image classifiers (MLP, CNN, LeNet5, ResNet18/50, EfficientNet).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Loaded image classifier checkpoints rebuild the backbone on CPU (
torch.load(..., map_location="cpu")), butpredictmoved only the input images to the device. This caused aRuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the sameduring prediction. The model is now moved to the device before inference in every image classifier.Type of Change
Testing
Changes (by file)
DashAI/back/models/base_torchvision_image_classifier.py: addself.model.to(self.device)before the eval loop inpredict(covers ResNet18, ResNet50, EfficientNet).DashAI/back/models/cnn_image_classifier.py: same fix inpredict.DashAI/back/models/lenet5_image_classifier.py: same fix inpredict.DashAI/back/models/mlp_image_classifier.py: same fix inpredict.