ResNet Bottleneck Architecture #1957
Closed
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
|
Notice that this neural network will likely only work in the training loop with the fixed bug of nested lists from #1956 |
|
Hi @MaximilianSchreff , thanks a lot for working on this. Nice to see that the code is document in the functions. can we create one small .md file with instructions on how to run, limitations, a quick example! If you have any images/diagrams (even hand drawn rough diagrams also fine). May be like this: https://pytorch.org/hub/nvidia_deeplearningexamples_resnet50/ Regards |
|
@j143 Thank you for the feedback! |
|
Content merged by other PR |
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Outdated suggestions cannot be applied.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.
This series of commits adds the forward pass of the residual network bottleneck architecture as introduces by "Deep Residual Learning for Image Recognition" by Kaiming He et. al. and refined in "ResNet v1.5 for PyTorch" by NVIDIA.
The individual components (bottleneck residual block, bottleneck residual layer) has been unit tested and the tests were added to the NN test suite and the whole bottleneck ResNet has been tested against the implementation of PyTorch which was not added to the test suite.
@phaniarnab