Tensorflow TRT Colab fix #1447
Open
Tensorflow TRT Colab fix #1447
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
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Outdated suggestions cannot be applied.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.
The original TensorFlow-TensorRT (TF-TRT) notebooks in the tensorflow/tensorrt repository are outdated and no longer function correctly with newer TensorFlow versions. Additionally, this repository has been archived, and it is unclear if TensorFlow will continue supporting TensorRT in future releases.
Problem Statement
The existing Colab notebooks fail to run on TensorFlow 2.1+, showing the error:
"RuntimeError: TensorFlow has not been built with TensorRT support. "
TensorFlow 2.18.0 and later no longer support TensorRT, making 2.17.0 the last confirmed version with working TF-TRT integration.
The current TensorRT integration is undocumented in TensorFlow 2.17.0.
Proposed Fix & Changes
Updated the Colab notebook to work with TensorFlow 2.17.0, ensuring proper CUDA and TensorRT compatibility.
Added installation instructions for the required libnvinfer8 and libnvinfer-plugin8 packages.
Provided a step-by-step guide along with the code to run inference with TF-TRT for a classical Image classification usecase.
Next Steps
If TensorFlow 2.19+ reintroduces TensorRT support, the documentation should be updated accordingly.
Consider maintaining an official compatibility matrix for TF-TRT going forward.
References:
Original TensorFlow-TensorRT Repository (Archived)
NVIDIA Developer Forum Discussion