🤗 HuggingFace Hub Integration

• Use yolov5 models from hub:

import yolov5

# load model
model = yolov5.load('fcakyon/yolov5s-v7.0')

# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'

# perform inference
results = model(img, size=640)

# show detection bounding boxes on image
results.show()

• Fine-tune yolov5 models from hub:

yolov5 train --img 640 --batch 16 --weights fcakyon/yolov5s-v7.0 --epochs 10 --device cuda:0

• Automatically push fine-tuned weight and training logs to hub (with autogenerated model card):

yolov5 train --data data.yaml --weights yolov5s.pt --hf_model_id username/modelname --hf_token YOUR-HF-WRITE-TOKEN

Available models: https://huggingface.co/models?other=yolov5

What's Changed

• ad hf hub tests to package testing by @fcakyon in https://github.com/fcakyon/yolov5-pip/pull/177
• fix private hub model download by @fcakyon in https://github.com/fcakyon/yolov5-pip/pull/179
• add automatic hf hub upload, refactor helpers by @fcakyon in https://github.com/fcakyon/yolov5-pip/pull/180
• fix readme by @fcakyon in https://github.com/fcakyon/yolov5-pip/pull/181

Full Changelog: https://github.com/fcakyon/yolov5-pip/compare/7.0.2...7.0.3