A clean, modular implementation of the Yolov7 model family, which uses the official pretrained weights, with utilities for training the model on custom (non-COCO) tasks.
does it should be the following?
[
[257, 258, 259, 260, 261, 262, 263, 264],
1,
detection_head,
[num_classes, anchor_sizes_per_layer, strides, True],
],
line 1152 - 1157 [ [257, 258, 259, 260, 261, 262, 263, 264], 1, detection_head, [num_channels, anchor_sizes_per_layer, strides, True], ],
does it should be the following? [ [257, 258, 259, 260, 261, 262, 263, 264], 1, detection_head, [num_classes, anchor_sizes_per_layer, strides, True], ],