smalldroid / yolov3-pytorch

annotation and specification for yolov3

Update

This repo has been updated to recent version.More details and annotations can be found in code.

yolov3-pytorch

Annotation and Specification for yolov3

Attention:Inputs should be labeld the same as COCO (yolo format):normalized && cxywh

refer to:https://github.com/ultralytics/yolov3

detect

download yolov3.weights trained on COCO：https://pjreddie.com/darknet/yolo/

run python detect.py

train

You can test it on offerred image in /data/dataset
run python train.py
test on the same image to verify it feasibility.

This is my loss curls with testing on single picture for 100 epochs,it does converge well.
Run train-vis.py to monitor loss.