Make profiling return pre- and post-optimization plots (up to 4 plots in total) #323
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
added 6 commits
April 7, 2021 18:04
added 4 commits
April 20, 2021 14:09
This reverts commit d71f989
instead of being obtained from a pre-optimisation graph copy
thesps
reviewed
Apr 22, 2021
thesps
reviewed
Apr 22, 2021
thesps
approved these changes
Apr 23, 2021
calad0i
pushed a commit
to calad0i/hls4ml
that referenced
this pull request
Jul 1, 2023
…-4-plots Make profiling return pre- and post-optimization plots (up to 4 plots in total)
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Outdated suggestions cannot be applied.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.
Currently,
hls4ml.model.profiling.numerical()returns 2 profiling plots, most often showing HLSModel and Keras/PyTorch/... layers with HLSModel data types overlaid. These may be confusing because hls4ml applies optimizations resulting in differences between final HLSModel and Keras/PyTorch/... layers.This PR attempts to resolve this problem by making
hls4ml.model.profiling.numerical()return up to 4 plots instead of 2: predominantly weights of HLSModel layers before and after optimizations + activations/outputs of HLSModel/Keras/PyTorch/... layers before and after optimizations.