You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
使用数据集训练之后保存权值到log文件夹中,随后将权值的路径复制到yolo.py的model_path中,再使用get_map.py计算map,在该阶段出现权值不匹配问题。
RuntimeError: Error(s) in loading state_dict for YoloBody:
size mismatch for yolo_head_P3.weight: copying a param with shape torch.Size([1071, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([255, 128, 1, 1]).
size mismatch for yolo_head_P3.bias: copying a param with shape torch.Size([1071]) from checkpoint, the shape in current model is torch.Size([255]).
size mismatch for yolo_head_P4.weight: copying a param with shape torch.Size([1071, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([255, 256, 1, 1]).
size mismatch for yolo_head_P4.bias: copying a param with shape torch.Size([1071]) from checkpoint, the shape in current model is torch.Size([255]).
size mismatch for yolo_head_P5.weight: copying a param with shape torch.Size([1071, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([255, 512, 1, 1]).
size mismatch for yolo_head_P5.bias: copying a param with shape torch.Size([1071]) from checkpoint, the shape in current model is torch.Size([255]).
The text was updated successfully, but these errors were encountered:
使用数据集训练之后保存权值到log文件夹中,随后将权值的路径复制到yolo.py的model_path中,再使用get_map.py计算map,在该阶段出现权值不匹配问题。
RuntimeError: Error(s) in loading state_dict for YoloBody:
size mismatch for yolo_head_P3.weight: copying a param with shape torch.Size([1071, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([255, 128, 1, 1]).
size mismatch for yolo_head_P3.bias: copying a param with shape torch.Size([1071]) from checkpoint, the shape in current model is torch.Size([255]).
size mismatch for yolo_head_P4.weight: copying a param with shape torch.Size([1071, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([255, 256, 1, 1]).
size mismatch for yolo_head_P4.bias: copying a param with shape torch.Size([1071]) from checkpoint, the shape in current model is torch.Size([255]).
size mismatch for yolo_head_P5.weight: copying a param with shape torch.Size([1071, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([255, 512, 1, 1]).
size mismatch for yolo_head_P5.bias: copying a param with shape torch.Size([1071]) from checkpoint, the shape in current model is torch.Size([255]).
The text was updated successfully, but these errors were encountered: