# 1only batches of spatial targets supported (non-empty 3D tensors) but got targets of size: : \[1, 3, 375, 1242\] **URL:** \ **Category:** vision\ **Created:** [December 20, 2018, 1:37am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609 "2018-12-20T01:37:14Z")\ **Posts on this page:** 20\ **Page:** 2
**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:** [January 4, 2019, 9:30pm UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/22 "2019-01-04T21:30:29Z")
If the mapping is not given in the dataset (or the hosting website) somewhere, you could just create your own mapping like I did for the medical segmentation dataset. Which dataset are you using? Maybe the mapping was already created somewhere. ---
**Author:** ![Xiaoyu\_Song](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xiaoyu_song/32/69467_2.png) [@Xiaoyu\_Song](https://discuss.pytorch.org/u/Xiaoyu_Song)\ **Post date:** [January 8, 2019, 5:25am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/23 "2019-01-08T05:25:10Z")
Thank you for your reply, could you give me the link of your example for the medical segmentation dataset? Here is the dataset I used: > [@1only batches of spatial targets supported (non-empty 3D tensors) but got targets of size: : \[1, 3, 375, 1242\]](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/15): > > Thank you for your explanation, I’m using the [KITTI semantic segmentation datasets](http://www.cvlibs.net/datasets/kitti/eval_semseg.php?benchmark=semantics2015). which are conform with [The Cityscapes Dataset](https://www.cityscapes-dataset.com/), it has 30 classes. But I didn’t find the key value pair between my colour codes and the corresponding class index. I have seen the post you mentioned, and I don’t know the class mapping value neither, could you help? ---
**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:** [January 8, 2019, 12:47pm UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/24 "2019-01-08T12:47:01Z")
Sure! @Neda used the TEM dataset from [here](https://lmb.informatik.uni-freiburg.de/resources/datasets/tem.en.html). I just downloaded it and created a pseudo-mapping using all unique values in the images, since I couldn’t find an official color-to-label mapping. ---
**Author:** ![Xiaoyu\_Song](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xiaoyu_song/32/69467_2.png) [@Xiaoyu\_Song](https://discuss.pytorch.org/u/Xiaoyu_Song)\ **Post date:** [January 9, 2019, 2:42am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/25 "2019-01-09T02:42:21Z")
I’m just wondering how you create your pseudo-mapping ? You print all values in the images and observe the difference? When I try to print the image, It only shows me very small part of the data, and normally for one image, the data is very large, so could you tell me how you can observe all _ **different unique values** _ in one image and then create the mapping. ---
**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:** [January 9, 2019, 7:55am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/26 "2019-01-09T07:55:02Z")
You could try the following code using `torch.unique` and the `dim` argument: ```python image = Image.open(path) im_arr = np.array(image) im_tensor = torch.from_numpy(im_arr) im_tensor = im_tensor.permute(2, 0, 1) unique_colors = torch.unique(im_tensor.view(im_tensor.size(0), -1), dim=1) ``` Let me know, if that works for you! ---
**Author:** ![Xiaoyu\_Song](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xiaoyu_song/32/69467_2.png) [@Xiaoyu\_Song](https://discuss.pytorch.org/u/Xiaoyu_Song)\ **Post date:** [January 10, 2019, 1:43am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/27 "2019-01-10T01:43:43Z")
Thank you very much 😄, this works! Here is my code: ```auto colors = torch.tensor([]) for i in range(len(trainmask)): im_str = trainimage[i] im_arr = io.imread(os.path.join(train_mask, im_str)) im_tensor = torch.from_numpy(im_arr) im_tensor = im_tensor.permute(2,0,1) unique_colors = torch.unique(im_tensor.view(im_tensor.size(0), -1)).type(torch.FloatTensor) colors = torch.cat((colors, unique_colors)) colors = torch.unique(colors) print(colors) ``` and here is the result: ```auto tensor([ 64., 150., 107., 110., 20., 220., 119., 180., 11., 152., 0., 160., 60., 102., 230., 81., 255., 120., 30., 100., 80., 140., 251., 142., 74., 111., 90., 35., 156., 190., 170., 153., 32., 250., 244., 165., 128., 70., 130., 232.]) ``` There are 40 unique colour in my mask image. It means that I have 40 unique class in my dataset. I’m now wondering how to find the relationship between these colour value and the class type. Do you have some suggestions? ---
**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:** [January 10, 2019, 2:35am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/28 "2019-01-10T02:35:41Z")
I’m not that sure about the last `unique` call. `unique_colors` should be a `[number_of_colors, 3]` tensor so that each unique color contains the RGB values. Currently you are calling unique again on it, so that the RGB color is not usable anymore. Anyway, if you’ve fixed this and can’t find any official mapping, I would just create a `dict` with your own mapping and stick to it. In the end you just need class indices for the different colors. It doesn’t matter if car has the class index 0 or 40 as long as you don’t mix it up. 😉 ---
**Author:** ![Xiaoyu\_Song](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xiaoyu_song/32/69467_2.png) [@Xiaoyu\_Song](https://discuss.pytorch.org/u/Xiaoyu_Song)\ **Post date:** [January 10, 2019, 2:56am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/29 "2019-01-10T02:56:28Z")
Do you mean I should specify the dimension of the unique to get `[number_of_colors, 3]`? I try to specify the dimension of the unique, when I add `dim=1`, I get this error: ```auto unique() got an unexpected keyword argument 'dim' ``` my torch version is 0.4.1 Do you know what’s wrong?😃 ---
**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:** [January 10, 2019, 3:01am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/30 "2019-01-10T03:01:52Z")
The dim argument was added after the `0.4.1` release, so I would recommend to update to the latest stable release (`1.0`) to get this and other useful features. 😉 ---
**Author:** ![Xiaoyu\_Song](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xiaoyu_song/32/69467_2.png) [@Xiaoyu\_Song](https://discuss.pytorch.org/u/Xiaoyu_Song)\ **Post date:** [January 10, 2019, 10:35am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/35 "2019-01-10T10:35:09Z")
Problem solved, here is my code: ```auto colors_all = torch.tensor([]) for i in range(len(mask_list)): mask_str = mask_list[i] mask_arr = io.imread(os.path.join(mask_dir, mask_str)) mask_tensor = torch.from_numpy(mask_arr) mask_tensor = mask_tensor.permute(2,0,1) # print(mask_tensor.shape) colors = torch.unique(mask_tensor.view(mask_tensor.size(0), -1),dim=1) colors = colors.permute(1,0).type(torch.FloatTensor) colors_all = torch.cat((colors_all, colors)) colors_unique = torch.unique(colors_all, dim = 0) print(colors_unique.shape) print(colors_unique) ``` Here is the results: ```auto torch.Size([29, 3]) tensor([[0., 0., 0.], [0., 0., 70.], [0., 0., 90.], [0., 0., 110.], [0., 0., 142.], [0., 0., 230.], [0., 60., 100.], [0., 80., 100.], [70., 70., 70.], [70., 130., 180.], [81., 0., 81.], [102., 102., 156.], [107., 142., 35.], [111., 74., 0.], [119., 11., 32.], [128., 64., 128.], [150., 100., 100.], [150., 120., 90.], [152., 251., 152.], [153., 153., 153.], [180., 165., 180.], [190., 153., 153.], [220., 20., 60.], [220., 220., 0.], [230., 150., 140.], [244., 35., 232.], [250., 170., 30.], [250., 170., 160.], [255., 0., 0.]]) ``` There are in total 29 classes 🤣 ---
**Author:** ![Xiaoyu\_Song](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xiaoyu_song/32/69467_2.png) [@Xiaoyu\_Song](https://discuss.pytorch.org/u/Xiaoyu_Song)\ **Post date:** [January 11, 2019, 7:24am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/36 "2019-01-11T07:24:51Z")
@ptrblck I have one question concerning the mapping, I have read your mapping example, which is for example: 85:0 In my case, I have 29 unique classes in total, and my mask is size 3x375x1242, after these code below: ```auto mask_tensor = mask_tensor.permute(2,0,1) mask_tensor = mask_tensor.view(mask_tensor.size(0), -1).permute(1,0) ``` I get the mask size : `torch.Size([465750, 3])` so the unique color is 1 x 3, mask is 465750 x 3 now. the mapping is : ```auto self.mapping = { torch.tensor([0, 0, 0], dtype=torch.uint8):0, torch.tensor([0, 0, 70], dtype=torch.uint8):1, torch.tensor([0, 0, 90], dtype=torch.uint8):2, torch.tensor([0, 0, 110], dtype=torch.uint8):3, torch.tensor([0, 0, 142], dtype=torch.uint8):4, torch.tensor([0, 0, 230], dtype=torch.uint8):5, torch.tensor([0, 60, 100], dtype=torch.uint8):6, torch.tensor([0, 80, 100.], dtype=torch.uint8):7, torch.tensor([70, 70, 70], dtype=torch.uint8):8, torch.tensor([70, 130, 180], dtype=torch.uint8):9, torch.tensor([81, 0, 81], dtype=torch.uint8):10, torch.tensor([102, 102, 156], dtype=torch.uint8):11, torch.tensor([107, 142, 35], dtype=torch.uint8):12, torch.tensor([111, 74, 0], dtype=torch.uint8):13, torch.tensor([119, 11, 32], dtype=torch.uint8):14, torch.tensor([128, 64, 128], dtype=torch.uint8):15, torch.tensor([150, 100, 100], dtype=torch.uint8):16, torch.tensor([150, 120, 90], dtype=torch.uint8):17, torch.tensor([152, 251, 152], dtype=torch.uint8):18, torch.tensor([153, 153, 153], dtype=torch.uint8):19, torch.tensor([180, 165, 180], dtype=torch.uint8):20, torch.tensor([190, 153, 153], dtype=torch.uint8):21, torch.tensor([220, 20, 60], dtype=torch.uint8):22, torch.tensor([220, 220, 0], dtype=torch.uint8):23, torch.tensor([230, 150, 140], dtype=torch.uint8):24, torch.tensor([244, 35, 232], dtype=torch.uint8):25, torch.tensor([250, 170, 30], dtype=torch.uint8):26, torch.tensor([250, 170, 160], dtype=torch.uint8):27, torch.tensor([255, 0, 0], dtype=torch.uint8):28 } def mask_to_class(self, mask): for k in self.mapping: # print(k.dtype) # print(mask.dtype) mask[mask==k] = self.mapping[k] return mask def __getitem__ (self, idx): img_list = os.listdir(img_dir) mask_list = os.listdir(mask_dir) img_str = img_list[idx] img_arr = io.imread(os.path.join(img_dir, img_str)) img_tensor = torch.from_numpy(img_arr) img_tensor = img_tensor.permute(2,0,1) mask_str = mask_list[idx] mask_arr = io.imread(os.path.join(mask_dir, mask_str)) mask_tensor = torch.from_numpy(mask_arr) mask_tensor = mask_tensor.permute(2,0,1) mask_tensor = mask_tensor.view(mask_tensor.size(0), -1).permute(1,0) print(mask_tensor) print(mask_tensor.shape) mask_tensor = self.mask_to_class(mask_tensor) print(mask_tensor.shape) sample = {'image':img_tensor, 'mask':mask_tensor} ``` after the mapping, the mask is still the size 465750 x 3. Here is the example of the mask values before and after mapping: ```auto tensor([[70, 130, 180], [70, 130, 180], [70, 130, 180], ..., [244, 35, 232], [244, 35, 232], [244, 35, 232]], dtype=torch.uint8) tensor([[8, 9, 9], [8, 9, 9], [8, 9, 9], ..., [25, 25, 25], [25, 25, 25], [25, 25, 25]], dtype=torch.uint8) ``` I don’t understand why 1. In the mapping, the 1x3 tensor is mapped to an integer, why the mapped mask size doesn’t change. 2. If I get the mapped mask value above, is it correct? 3. If it’s correct, what are the values in the mapped mask represent? For example, in the first [8,9,9] tensor, the 8 is a class , 9 is a class. I’m confused. Could you give me some explanations? ---
**Author:** ![john\_john](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/j/8797f3/32.png) [@john\_john](https://discuss.pytorch.org/u/john_john)\ **Post date:** [January 22, 2019, 2:50am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/37 "2019-01-22T02:50:32Z")
Do you have the Cityscapes dataset ? ---
**Author:** ![Xiaoyu\_Song](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xiaoyu_song/32/69467_2.png) [@Xiaoyu\_Song](https://discuss.pytorch.org/u/Xiaoyu_Song)\ **Post date:** [January 22, 2019, 4:30am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/38 "2019-01-22T04:30:35Z")
Hi, I use the KITTI data set [KITTI semantic segmentation datasets](http://www.cvlibs.net/datasets/kitti/eval_semseg.php?benchmark=semantics2015). ---
**Author:** ![john\_john](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/j/8797f3/32.png) [@john\_john](https://discuss.pytorch.org/u/john_john)\ **Post date:** [January 22, 2019, 9:40am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/39 "2019-01-22T09:40:02Z")
Thank you, do you have a email ？ ---
**Author:** ![Xiaoyu\_Song](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/xiaoyu_song/32/69467_2.png) [@Xiaoyu\_Song](https://discuss.pytorch.org/u/Xiaoyu_Song)\ **Post date:** [January 23, 2019, 5:42am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/40 "2019-01-23T05:42:17Z")
yes. xysong@ntu.edu.sg ---
**Author:** ![DonFawaz](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/d/c68b51/32.png) [@DonFawaz](https://discuss.pytorch.org/u/DonFawaz)\ **Post date:** [May 29, 2019, 2:14pm UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/41 "2019-05-29T14:14:49Z")
hi, can you explain how the mapping work with you ? ---
**Author:** ![noornk](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/noornk/32/12076_2.png) [@noornk](https://discuss.pytorch.org/u/noornk)\ **Post date:** [July 11, 2019, 3:34am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/42 "2019-07-11T03:34:16Z")
@ptrblck I have the same error, and I’m mapping the values to class labels, which are either 0, or 1. Could you please help me? ---
**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:** [July 11, 2019, 10:52am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/43 "2019-07-11T10:52:26Z")
Could you post a code snippet to reproduce this issue? Interesting would be the input, output, their shapes, min/max values and the criterion you are using. ---
**Author:** ![noornk](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/noornk/32/12076_2.png) [@noornk](https://discuss.pytorch.org/u/noornk)\ **Post date:** [July 11, 2019, 1:58pm UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/44 "2019-07-11T13:58:36Z")
I’ve found the issue. because of my problem discussed in another post, I’m trying different networks implemented by others to see where my problem is. @ptrblck This is the link to my project: [https://github.com/noornk/U-Net](https://github.com/noornk/U-Net) My images are mammographies, and I’ve produced png’s for mask, from xml files. I have problem visualizing the result for test. Although because of this problem, I’m not sure if my U-Net is working well or not. ---
**Author:** ![ynulonger](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ynulonger/32/20836_2.png) [@ynulonger](https://discuss.pytorch.org/u/ynulonger)\ **Post date:** [February 22, 2020, 4:49am UTC](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609/45 "2020-02-22T04:49:48Z")
Hi, I got a similar error. I am doing image segmentation now, there are 4 classes for pixels. So, originally the shape of my mask is [-1, 32, 32, 4]. Then I map the mask into [-1, 32, 32]. But I got another error, that is: ```auto RuntimeError: input and target batch or spatial sizes don't match: target [128 x 32 x 32], input [128 x 32 x 32 x 4] at /pytorch/aten/src/THCUNN/generic/SpatialClassNLLCriterion.cu:23 ``` Here is my code: ```auto criterion = nn.CrossEntropyLoss().cuda() optimizer = optim.Adam(model.parameters()) for batch_idx, (data, target) in enumerate(train_loader,1): if args.cuda: data, target = data.cuda(), target.cuda() optimizer.zero_grad() print(type(data)) output = model(data) loss = criterion(output, target.long()) loss.backward() optimizer.step() ``` The shape of output is [-1, 32, 32, 4] How can I solve this error? Help 😂 [Previous page](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609.md?page=1) [Next page](https://discuss.pytorch.org/t/1only-batches-of-spatial-targets-supported-non-empty-3d-tensors-but-got-targets-of-size-1-3-375-1242/32609.md?page=3)