Changes to be able to convert the .pt model to ONNX and TensorRT formats #91
Conversation
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
disable batch statistics as we are not training the batch statistics were forgotten to set to False. the batchnorm function gave some errors with tf2onnx converter TensorRT does not support uint8 so one output was converted to int64 instead Add code to save the model to folder tmp
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Outdated suggestions cannot be applied.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.
Greetings,
I have created this PR merely to present the changes necessary to be able to use the pre-trained ELG model in TensorRT code. I also added some details to README about installation and software requirements as they were lacking some details.
My PR doesn't necessarily have to be merged on swook/GazeML but I wanted to leave this here to save somebody else time if they want to do the things I did.