Musa Mahmood
cb21b73460
- segmentation-plan.html: the plan for panoptic segmentation of images, per library folder, stored
in .mcap chunks (no file version bump), in six phases.
- tools/export_mask2former.py: exports facebook/mask2former-swin-base-coco-panoptic to ONNX (opset 17,
dynamic batch, 384 x 384 input) and checks it against PyTorch: on 25 images, all 180 segments
identical (IoU 1.000). Writes the class list with names for people ("sky-other-merged" is "sky"),
and PyTorch's own segmentations for segment-probe -check.
- modules/Segment: runs the model with onnxruntime (CUDA, else the CPU) and makes segments of its
outputs as transformers' post_process_panoptic_segmentation does: a segment id map (longest side at
most 1024) and each segment's class, score, area and bounds. Matches PyTorch on 99.8% of pixels,
every segment scored 0.6 or more found. 57 ms an image at batch 4 on an RTX 5080 laptop.
- tools/segment_probe.jai (jai first.jai - segment_probe): segments image files; -out draws them,
-check compares with PyTorch, -dump-input writes the model's input.
- modules/onnxruntime: ort_run_float_outputs, for a model with several outputs.
- first.jai copies the model to bin/segment-models. The model itself is not in git
(modules/Segment/models, 462 MB); tools/export_mask2former.py makes it.
30 lines
761 B
Plaintext
30 lines
761 B
Plaintext
# Build output: binaries, copied assets and logs go to bin/, intermediates to .build/ (the
|
|
# binding generators in modules/ make their own).
|
|
/bin/
|
|
/bin-headless/
|
|
.build/
|
|
|
|
# Debuggers and editors
|
|
*.rdi
|
|
.vs/
|
|
.vscode/
|
|
*.10x
|
|
# fork.jai writes one with this machine's paths
|
|
*.focus-config
|
|
|
|
# OS and sync clutter
|
|
.DS_Store
|
|
Thumbs.db
|
|
.stfolder
|
|
|
|
# OCR: downloaded, not committed (modules/onnxruntime/fetch.jai, modules/OCR/fetch_models.jai)
|
|
/modules/onnxruntime/windows/
|
|
/modules/onnxruntime/linux/
|
|
/modules/onnxruntime/macos/
|
|
/modules/onnxruntime/download/
|
|
/modules/OCR/models/
|
|
# Labels: downloaded, not committed (modules/Labels/fetch_models.jai)
|
|
/modules/Labels/models/
|
|
# Segmentation: exported by tools/export_mask2former.py, not committed
|
|
/modules/Segment/models/
|