A parameter with shape torch. Size ([262]) is copied from the checkpoint, and the shape in the current model is torch. Size ([290]).

The parameter size of fc.weight does not match, just modify the parameter.

VIM open the corresponding file and modify the parameters

Solve the problem successfully

Reference link

Read More:

• ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256,
• raise ValueError(‘Expected input batch_size ({}) to match target batch_size ({}).‘
• Spring boot does not take effect when using @ size to verify a single set parameter of the control layer
• (26)RuntimeError: Error(s) in loading state_dict for YoloBody:size mismatch for yolo_head3.1.weight
• Internalerror: blas GEMM launch failed: A. shape = (100, 784), B. shape = (784, 10), M = 100, n = 10… Problem solving
• Error: The size of the connection buffer (131072) was not large enough
• Idea error: error in method comment @ param parameter
• Error: cannot allocate vector of size 88.1 MB
• Linux view folder size, remaining disk space (DU / DF)
• Python opencv (3) get image size
• Solve the problem that “figure size 640×480 with 1 axes” does not display pictures in jupyter notebook
• mysql5.7.26：[ERR] 1118 – Row size too large (＞ 8126)
• Latex bracket size control
• Error in comparing the size function of STL with negative number
• RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the
• RuntimeError: Expected hidden[0] size (x, x, x), got(x, x, x)
• Solve gitbook rangeerror: maximum call stack size exceeded