get_map.py

[mimi37]

B导，我直接装载yolo_l.pth，同时也在yolo.py修改了phi=l，但是运行get_map.py缺报错如下，辛苦帮忙看下问题，我感觉是对应的呀。 yolo = YOLO(model_path = model_path,confidence = confidence, nms_iou = nms_iou, modify=-1)
RuntimeError: Error(s) in loading state_dict for YoloBody:
size mismatch for yolo_head_P3.weight: copying a param with shape torch.Size([255, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([75, 256, 1, 1]).
size mismatch for yolo_head_P3.bias: copying a param with shape torch.Size([255]) from checkpoint, the shape in current model is torch.Size([75]).
size mismatch for yolo_head_P4.weight: copying a param with shape torch.Size([255, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([75, 512, 1, 1]).
size mismatch for yolo_head_P4.bias: copying a param with shape torch.Size([255]) from checkpoint, the shape in current model is torch.Size([75]).
size mismatch for yolo_head_P5.weight: copying a param with shape torch.Size([255, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([75, 1024, 1, 1]).
size mismatch for yolo_head_P5.bias: copying a param with shape torch.Size([255]) from checkpoint, the shape in current model is torch.Size([75]).

[mimi37]

为啥预训练模型的head部分最后的C=255呢？想问一下怎么解决，谢谢！