# Sizes of tensors must match except in dimension 1 **URL:** \ **Category:** nlp\ **Created:** [March 29, 2022, 8:55pm UTC](https://discuss.pytorch.org/t/sizes-of-tensors-must-match-except-in-dimension-1/147785 "2022-03-29T20:55:09Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Gorgen](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/g/f14d63/32.png) [@Gorgen](https://discuss.pytorch.org/u/Gorgen)\ **Post date:** [March 29, 2022, 8:55pm UTC](https://discuss.pytorch.org/t/sizes-of-tensors-must-match-except-in-dimension-1/147785/1 "2022-03-29T20:55:09Z")
Dear everyone: when i train the model. it reported Expected size 7 but got size 5 for tensor number 1 in the list. I don’t know what expected object is needed to be 7. Could you please help me to fix this issue? Thanks, best wishes Traceback (most recent call last): File “train\_meld.py”, line 238, in test\_loss, test\_acc, test\_label, test\_pred, test\_mask, test\_fscore, attentions = train\_or\_eval\_model(model, loss\_function, test\_loader, e) File “train\_meld.py”, line 83, in train\_or\_eval\_model log\_prob, \_, alpha, alpha\_f, alpha\_b, \_ = model(r1, r2, r3, r4, audio\_feature, x5, x6, x1, o2, File “F:\Anaconda3\lib\site-packages\torch\nn\modules\module.py”, line 1110, in \_call\_impl return forward\_call(\*input, \*\*kwargs) File “F:\Projects\declare\Cosmic\_mfcc\_rnn\CommonsenseGRUModel.py”, line 94, in forward mixed\_feature = torch.cat((r, audio\_feature), dim=-1) # [seq\_len, batch\_size, dim\_mixed\_feature] RuntimeError: Sizes of tensors must match except in dimension 2. Expected size 7 but got size 5 for tensor number 1 in the list. ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [March 29, 2022, 11:00pm UTC](https://discuss.pytorch.org/t/sizes-of-tensors-must-match-except-in-dimension-1/147785/2 "2022-03-29T23:00:43Z")
The shape mismatch is raised in: ```python mixed_feature = torch.cat((r, audio_feature), dim=-1) ``` which seems to try to concatenate two 3-dimensional tensors in `dim2`. Based on this all dimensions should have the same size besides `dim2` which is not the case as seen in this small examples: ```python r = torch.randn(2, 7, 7) audio_feature = torch.randn(2, 5, 1) mixed_feature = torch.cat((r, audio_feature), dim=-1) > RuntimeError: Sizes of tensors must match except in dimension 2. Expected size 7 but got size 5 for tensor number 1 in the list. ``` As you can see, the size in `dim1` is different and set to `7` and `5` in these tensors. ---
**Author:** ![Gorgen](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/g/f14d63/32.png) [@Gorgen](https://discuss.pytorch.org/u/Gorgen)\ **Post date:** [March 30, 2022, 8:38am UTC](https://discuss.pytorch.org/t/sizes-of-tensors-must-match-except-in-dimension-1/147785/3 "2022-03-30T08:38:55Z")
Dear @ptrblck : thank you for your suggestions. To be honest. I follow your other answer about the similar issues. [RuntimeError: Sizes of tensors must match except in dimension 1](https://discuss.pytorch.org/t/runtimeerror-sizes-of-tensors-must-match-except-in-dimension-1/140651). I know the issue. However,none of the samples on r have that dimension is 7. Since any sample without r does not have a dimension of 7, why is there a prompt for a dimension of 7? I’m sorry, I’m constantly trying to debug to find the problem. Can you give me some advice, where should I place breakpoints to effectively identify the problem. Thank you for answering this really stupid sounding question. Thanks. best wishes ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [March 30, 2022, 9:37am UTC](https://discuss.pytorch.org/t/sizes-of-tensors-must-match-except-in-dimension-1/147785/4 "2022-03-30T09:37:48Z")
I would suggest to add a debug print statement right before the failing `torch.cat` operation as: ```python print(r.shape) print(audio_features.shape) mixed_features = torch.cat((r, audio_features), dim=-1) ``` and check if the shape might change in a specific iteration. ---
**Author:** ![Gorgen](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/g/f14d63/32.png) [@Gorgen](https://discuss.pytorch.org/u/Gorgen)\ **Post date:** [March 30, 2022, 10:17am UTC](https://discuss.pytorch.org/t/sizes-of-tensors-must-match-except-in-dimension-1/147785/5 "2022-03-30T10:17:55Z")
I appreciate your detailed advice. Thanks. Best wishes ---
**Author:** ![Hassan\_Ghavidel](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/hassan_ghavidel/32/71175_2.png) [@Hassan\_Ghavidel](https://discuss.pytorch.org/u/Hassan_Ghavidel)\ **Post date:** [August 3, 2024, 10:15pm UTC](https://discuss.pytorch.org/t/sizes-of-tensors-must-match-except-in-dimension-1/147785/6 "2024-08-03T22:15:35Z")
Hi @ptrblck I HAVE the same issue. how can we fix it? i receive the error RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 48 but got size 47 for tensor number 1 in the list. here: def forward(self, x, skip=None): x = self.up(x) if skip is not None: print(f"Shape of x : {x.shape}“) print(f"Shape of skip: {skip.shape}”) x = torch.cat([x, skip], dim=1) x = self.conv1(x) x = self.conv2(x) return x the shape of x and skip are different Shape of x : torch.Size([2, 768, 24, 24]) Shape of skip: torch.Size([2, 384, 24, 24]) Shape of x : torch.Size([2, 384, 48, 48]) Shape of skip: torch.Size([2, 192, 47, 47]) ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [August 3, 2024, 10:26pm UTC](https://discuss.pytorch.org/t/sizes-of-tensors-must-match-except-in-dimension-1/147785/7 "2024-08-03T22:26:09Z")
The shape mismatch error is raised in the `torch.cat` operation since `x` and `skip` have different spatial sizes. Pad one of these tensors or slice the other one to create matching spatial sizes.