Export to ONNX at FP32 and TensorRT at FP16 done with export.py.Reproduce by python segment/val.py -data coco.yaml -weights yolov5s-seg.pt -batch 1 Values indicate inference speed only (NMS adds about 1ms per image). Speed averaged over 100 inference images using a Colab Pro A100 High-RAM instance.Reproduce by python segment/val.py -data coco.yaml -weights yolov5s-seg.pt Accuracy values are for single-model single-scale on COCO dataset. All checkpoints are trained to 300 epochs with SGD optimizer with lr0=0.01 and weight_decay=5e-5 at image size 640 and all default settings.We ran all speed tests on Google Colab Pro notebooks for easy reproducibility. We exported all models to ONNX FP32 for CPU speed tests and to TensorRT FP16 for GPU speed tests. We trained YOLOv5 segmentations models on COCO for 300 epochs at image size 640 using A100 GPUs. Reproduce by python val.py -data coco.yaml -img 1536 -iou 0.7 -augment TTA Test Time Augmentation includes reflection and scale augmentations.Reproduce by python val.py -data coco.yaml -img 640 -task speed -batch 1
0 Comments
Leave a Reply. |