This is a MobileNet v2 training and implementation of YOLOv3. Code is written with reference to https://github.com/eriklindernoren/PyTorch-YOLOv3, with modifications/corrections made.
Change as required:
Current example uses trainList.part data list file (modified from https://pjreddie.com/media/files/coco/trainvalno5k.part, where validation dataset is discarded). Refer to https://github.com/eriklindernoren/PyTorch-YOLOv3/blob/master/data/get_coco_dataset.sh to obtain dataset. trainDatasetDirectory and trainDatasetLabelDirectory argument indicates the image and label file location respectively (MobileNet COCO test has low mAP though)
Will add more info