YOLOv3 in PyTorch > ONNX > CoreML > TFLite
This release requires PyTorch >= v1.0.0 to function properly. Please install the latest version from https://github.com/pytorch/pytorch/releases
There are no breaking changes in this release.
train.py --multi-scale
will train each batch at a randomly selected image size from 320 to 608 pixels.webcam=True
in detect.py.detect.py --cfg cfg/yolov3-tiny.cfg --weights weights/yolov3-tiny.pt
detect.py --cfg cfg/yolov3-spp.cfg --weights weights/yolov3-spp.pt
ONNX_EXPORT = True
in models.py.batch_report
functionality. All of this functionality, including computation of TP, FP, FN, Precision, Recall and mAP is now done in test.py after each training epoch.test.py
should ideally output text files in the official COCO mAP format as well for external mAP computation https://github.com/ultralytics/yolov3/issues/2#issuecomment-434751531.This is an initial release. This repository currently works well for inference, with no known issues, with training still under development. Current COCO training mAP using this repo is 0.522 (at 416 x 416) after 62 epochs (using all default training settings, simply running python3 train.py
). We are exploring ways to improve this further.
Loss curves, Precision, Recall and mAP.
Recommend PyTorch >0 v1.0.0 to run this repo, which includes numerous bug fixes: https://github.com/pytorch/pytorch/releases
test.py
seems to be slightly different than the official COCO mAP code.test.py
to additionally output text files in the official COCO mAP format.