Closed Robotatron closed 1 year ago
Does training work without using cache_images?
Does training work without using cache_images?
I did not use any caching for this run (see my command line arguments above). I found the issue though, it was a broken .npy file that was created from a previous run with --cache disk
Running with
python seg/segment/train.py --data sagemaker.yaml --cfg yolov7s-seg.yaml --hyp hyp.scratch-high.yaml --img 480 --batch -1 --project runs/SageMaker/train --name 01-S-600-hyphigh
I've opened every image with PIL and converted every image to a "RGB" format. So if an image file was corrupt, PIL would notice that.
Error: