feat: add species classifier training pipeline #69
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
Add two scripts that orchestrate the full flow from a GBIF Darwin Core Archive (DwC-A) to a trained ConvNeXt-Tiny species classification model: - scripts/build_species_list.py: Bridge script that reads verbatimScientificName from a DwC-A (not included in load_dwca_data()), joins it onto the clean-dataset annotations CSV, and builds a category map JSON. - scripts/train_species_classifier.sh: Single bash script running all 7 pipeline steps with uv run: fetch-images, verify-images, clean-dataset, build_species_list.py, split-dataset, create-webdataset, train-model. Supports resuming (skips steps with existing outputs) and computes num_classes dynamically from the category map. No modifications to existing src/ code. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.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.
Summary
scripts/build_species_list.py, a bridge script that readsverbatimScientificNamefrom a DwC-A file (not included inload_dwca_data()) and joins it onto the clean-dataset annotations CSV. Also prints DwC-A summary stats and builds acategory_map.json.scripts/train_species_classifier.sh, a single bash script that orchestrates all 7 pipeline steps from DwC-A to trained ConvNeXt-Tiny model usinguv run. Each step checks for existing outputs to support resuming interrupted runs.src/code. The bridge script works aroundload_dwca_data()not includingverbatimScientificNamein its column selection.Pipeline steps:
fetch-images->verify-images->clean-dataset->build_species_list.py->split-dataset->create-webdataset->train-modelTest plan
category_map.jsoncontains correct species-to-ID mappingMIN_INSTANCES=3and default val/test fractions apply🤖 Generated with Claude Code