YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Were the pre-training weights in YOLOX trained on the coco dataset? I would like to use Convnext as the backbone of yolox, do I also need to get the pre-training weights by training on the coco dataset?
Were the pre-training weights in YOLOX trained on the coco dataset? I would like to use Convnext as the backbone of yolox, do I also need to get the pre-training weights by training on the coco dataset?