This repo provides a clean implementation of YoloV3 in TensorFlow 2.0 using all the best practices. I have created a complete tutorial on how to train from scratch using the VOC2012 Dataset. For customzied training, you need to generate tfrecord following the TensorFlow Object Detection API. For example you can use Microsoft VOTT to generate such dataset. You can also use this script to create the pascal voc dataset.

This repo provides a clean implementation of YoloV3 in TensorFlow 2.0 using all the best practices. I have created a complete tutorial on how to train from scratch using the VOC2012 Dataset. For customzied training, you need to generate tfrecord following the TensorFlow Object Detection API. For example you can use Microsoft VOTT to generate such dataset. You can also use this script to create the pascal voc dataset.

Languages, like human bodies, come in a variety of shapes--but only to a point. Just as people don't sprout multiple heads, languages tend to veer away from certain forms that might spring from an imaginative mind. For example, one core property of human languages is known as duality of patterning: meaningful linguistic units (such as words) break down into smaller meaningless units (sounds), so that the words sap, pass, and asp involve different combinations of the same sounds, even though their meanings are completely unrelated. It's not hard to imagine that things could have been otherwise. In principle, we could have a language in which sounds relate holistically to their meanings--a high-pitched yowl might mean "finger," a guttural purr might mean "dark," a yodel might mean "broccoli," and so on.