Hello, I would like to share with you my implementation of yolov3 object detector in tensorflow 2.2 https://github.com/emadboctorx/yolov3-keras-tf2
Features tensorflow-2.X--keras-functional-api cpu-gpu support Random weights and DarkNet weights support csv-xml annotation parsers. Anchor generator. `matplotlib` visualization of all stages. `tf.data` input pipeline. `pandas` & `numpy` data handling. `imgaug` augmentation pipeline `logging` coverage. All-in-1 custom trainer. Stop and resume training support. Fully vectorized mAP evaluation. `labelpix` support. Photo & video detection -- https://mail.python.org/mailman/listinfo/python-list
