Open monocongo opened 5 years ago
To clarify, I'm interested in transfer learning, i.e. taking a pre-trained model and further training it using my custom dataset of images/annotations. I'd like to do this for the YOLO and SDD models included here.
Currently, those models and ONNX support only inference. Regarding training and transfer learning, check the training work group: https://github.com/onnx/working-groups/tree/master/training
I would like to train the YOLOv3 model from this repository's model zoo, but there is no documentation describing that process. Can anyone advise? Thanks in advance for suggestions or insight.