This release requires PyTorch >= v1.0.0 to function properly. Please install the latest version from https://github.com/pytorch/pytorch/releases

Breaking Changes

There are no breaking changes in this release.

Bug Fixes

• N/A

Added Functionality

• MultiScale Training https://github.com/ultralytics/yolov3/issues/52: train.py --multi-scale will train each batch at a randomly selected image size from 320 to 608 pixels.
• Webcam Inference https://github.com/ultralytics/yolov3/issues/89: set webcam=True in detect.py.
• Video Inference. Pass a video file to detect.py.
• YOLOv3-tiny support https://github.com/ultralytics/yolov3/issues/51: detect.py --cfg cfg/yolov3-tiny.cfg --weights weights/yolov3-tiny.pt
• YOLOv3-spp support https://github.com/ultralytics/yolov3/issues/16. detect.py --cfg cfg/yolov3-spp.cfg --weights weights/yolov3-spp.pt
• ONNX Export https://github.com/ultralytics/yolov3/issues/82: ONNX_EXPORT = True in models.py.

Performance

• 20% improvement in training speed via code optimization and removal of redundant 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.

TODO (help and PR's welcome!)

• Multi GPU support https://github.com/ultralytics/yolov3/issues/21.
• YAPF linting (including possible wrap to PEP8 79 character-line standard) https://github.com/ultralytics/yolov3/issues/88.
• 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.