mcap/tools
Musa Mahmood 3b76b6dcb9 [0.1.26] gpu-bench: a memory trace per step, -ocr-workers and -ort-log
Each result now has the GPU's memory over the baseline after loading, the
first image, each warm-up pass and each timed pass (with the pass's peak), in
the output and as trace= in the results file, so growth across passes (a leak)
shows apart from a working set. -ocr-workers sets OCR's GPU worker threads, and
-ort-log info prints onnxruntime's arena extensions: what found the cause of
0.1.24's memory fix.
2026-10-17 21:13:30 -04:00
..
gpu_bench [0.1.26] gpu-bench: a memory trace per step, -ocr-workers and -ort-log 2026-10-17 21:13:30 -04:00
export_mask2former.py [0.0.11] Segmentation phases 1-2: Mask2Former exported to ONNX, and modules/Segment to run it 2026-10-10 03:39:28 +01:00
image_probe.jai [0.0.9] Import: videos and animated GIFs, in .mcap version 4 2026-10-09 23:10:55 +01:00
ocr_bench.jai [0.0.9] Import: videos and animated GIFs, in .mcap version 4 2026-10-09 23:10:55 +01:00
record_probe.jai [0.1.10] Recording toolbar: a System sound button beside Mic 2026-10-10 08:20:13 +01:00
segment_probe.jai [0.0.13] Segmentation phase 4: per-folder opt-in, the segmentation scan, -segment 2026-10-10 04:13:03 +01:00