Make the torchvision model architecture selectable by env var #3
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
|
Here's what this PR looks like when I test it on my computer: |
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Outdated suggestions cannot be applied.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 PR makes it possible to select the Torchvision model architecture used for model weights loaded from the
modelsdirectory, by setting a new environment variable namedTORCHVISION_MODEL_TYPE. If the environment variable is not set, then theefficientnet_v2_marchitecture is assumed; currently, the only other supported model type isefficientnet_v2_s, which is the architecture of https://github.com/PlanktoScope/streamlit-classification-app/releases/download/models%2Fdemo-1/effv2s_no_norm_DA+sh_20patience_256x256_50ep_loss.pth referenced inREADME.md.This PR also adds a feature flag to the Forklift package for the streamlit demo app to enable switching
TORCHVISION_MODEL_TYPEtoefficientnet_v2_saway from the default. Because theeffv2s_no_norm_DA+sh_20patience_256x256_50ep_loss.pthmodel weights file is the only publicly available file, the demo pallet in this repo enables that feature flag by default.