ONNX Model #316
Open
ONNX Model #316
Conversation
This file contains 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
The logic of Fourier transformation has been implemented from scratch without using complex numbers - the differences in results compared to the torch version are around thousandths of a percent. The code is intended for research purposes only, and the accuracy of the results is not guaranteed. This version can be exported using torch.onnx.export
Open
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Changelog:
torch.onnx.exportconverter (should give identical results to the original torch implementation).How to activate FourierUnitJIT:
You need to add the
use_jitboolean config field inconfig.yamlundergenerator/resnet_conv_kwargs, like this:config.generator.resnet_conv_kwargs.use_jit = True.