# Inconsistent tensor sizes at the last layer of SegNet **URL:** \ **Category:** vision\ **Created:** [April 13, 2018, 8:10pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388 "2018-04-13T20:10:50Z")\ **Posts on this page:** 20\ **Page:** 2
**Author:** ![Shounak\_Kundu](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/a88e4f/32.png) [@Shounak\_Kundu](https://discuss.pytorch.org/u/Shounak_Kundu)\ **Post date:** [April 19, 2018, 6:36pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/21 "2018-04-19T18:36:37Z")
Hi @ptrblck , thanks a lot for your help. I changed code as you mentioned. But , it seems to be consuming a lot of memory. ( I do not have GPU ). Here is my modified code : ```auto for epoch in range(1, num_epochs+1): epoch_loss = [] iteration=1 for step, (images, labels) in enumerate(trainLoader): print("Iter:"+str(iteration)) im_arr = np.array(labels) #print("Labels ==> ",np.unique(np.array(labels))) im_arr[(im_arr!=0) & (im_arr!=15) & (im_arr!=40)] = 0 # Set to classes im_arr[im_arr==15] = 1 im_arr[im_arr==40] = 2 #print(np.unique(im_arr)) iteration=iteration+1 inputs = Variable(images) targets = Variable(torch.from_numpy(im_arr)) outputs = model(inputs) optimizer.zero_grad() #print("outputs size ==> ",outputs.size()) #print("outputs[:,0] size ==> ",outputs[:,0].size()) #print("targets[:, 0] size ==> ",targets[:, 0].size()) #loss = criterion(outputs, targets[:, 0]) #print(targets[:,0]) loss = criterion(outputs,targets[:,0]) loss.backward() optimizer.step() epoch_loss.append(loss.data[0]) average = sum(epoch_loss) / len(epoch_loss) print("loss: "+str(average)+" epoch: "+str(epoch)+", step: "+str(step)) ``` Here is out-of-memory issues : ```auto Iter:1 /opt/anaconda/lib/python3.6/site-packages/torch/nn/modules/upsampling.py:180: UserWarning: nn.UpsamplingBilinear2d is deprecated. Use nn.Upsample instead. warnings.warn("nn.UpsamplingBilinear2d is deprecated. Use nn.Upsample instead.") /opt/anaconda/lib/python3.6/site-packages/torch/nn/functional.py:1423: UserWarning: nn.functional.upsample_bilinear is deprecated. Use nn.functional.upsample instead. warnings.warn("nn.functional.upsample_bilinear is deprecated. Use nn.functional.upsample instead.") /opt/anaconda/lib/python3.6/site-packages/ipykernel_launcher.py:13: UserWarning: Implicit dimension choice for log_softmax has been deprecated. Change the call to include dim=X as an argument. del sys.path[0] loss: 1.3778443336486816 epoch: 1, step: 0 Iter:2 --------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) in () 17 targets = Variable(torch.from_numpy(im_arr)) 18 ---> 19 outputs = model(inputs) 20 optimizer.zero_grad() 21 #print("outputs size ==> ",outputs.size()) /opt/anaconda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__ (self, *input, **kwargs) 323 for hook in self._forward_pre_hooks.values(): 324 hook(self, input) --> 325 result = self.forward(*input, **kwargs) 326 for hook in self._forward_hooks.values(): 327 hook_result = hook(self, input, result) in forward(self, x) 54 #print('layer2', x.size()) 55 ---> 56 x = self.layer3(x) 57 #print('layer3', x.size()) 58 /opt/anaconda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__ (self, *input, **kwargs) 323 for hook in self._forward_pre_hooks.values(): 324 hook(self, input) --> 325 result = self.forward(*input, **kwargs) 326 for hook in self._forward_hooks.values(): 327 hook_result = hook(self, input, result) /opt/anaconda/lib/python3.6/site-packages/torch/nn/modules/container.py in forward(self, input) 65 def forward(self, input): 66 for module in self._modules.values(): ---> 67 input = module(input) 68 return input 69 /opt/anaconda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__ (self, *input, **kwargs) 323 for hook in self._forward_pre_hooks.values(): 324 hook(self, input) --> 325 result = self.forward(*input, **kwargs) 326 for hook in self._forward_hooks.values(): 327 hook_result = hook(self, input, result) /opt/anaconda/lib/python3.6/site-packages/torchvision/models/resnet.py in forward(self, x) 74 residual = x 75 ---> 76 out = self.conv1(x) 77 out = self.bn1(out) 78 out = self.relu(out) /opt/anaconda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__ (self, *input, **kwargs) 323 for hook in self._forward_pre_hooks.values(): 324 hook(self, input) --> 325 result = self.forward(*input, **kwargs) 326 for hook in self._forward_hooks.values(): 327 hook_result = hook(self, input, result) /opt/anaconda/lib/python3.6/site-packages/torch/nn/modules/conv.py in forward(self, input) 275 def forward(self, input): 276 return F.conv2d(input, self.weight, self.bias, self.stride, --> 277 self.padding, self.dilation, self.groups) 278 279 /opt/anaconda/lib/python3.6/site-packages/torch/nn/functional.py in conv2d(input, weight, bias, stride, padding, dilation, groups) 88 _pair(0), groups, torch.backends.cudnn.benchmark, 89 torch.backends.cudnn.deterministic, torch.backends.cudnn.enabled) ---> 90 return f(input, weight, bias) 91 92 RuntimeError: $ Torch: not enough memory: you tried to allocate 0GB. Buy new RAM! at /opt/conda/conda-bld/pytorch_1513368888240/work/torch/lib/TH/THGeneral.c:246 ​ ``` Am I doing anything wrong here ? or is it just memory issue ? I am planning to move the code to a server having GPU. Will it solve this issue ? ---
**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:** [April 19, 2018, 7:44pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/22 "2018-04-19T19:44:09Z")
How much RAM does your machine have? I doubt the GPU will have more. How large is the batch size? Could you lower it? Also, you are using a lot of channels in your conv layers. Try to half them just to see if it’s working. ---
**Author:** ![Shounak\_Kundu](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/a88e4f/32.png) [@Shounak\_Kundu](https://discuss.pytorch.org/u/Shounak_Kundu)\ **Post date:** [April 20, 2018, 2:19am UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/23 "2018-04-20T02:19:49Z")
Hi @ptrblck , thanks for your reply. This is my memory information ```auto free total used free shared buff/cache available Mem: 65856408 4487936 58792948 4880 2575524 60738088 Swap: 31249404 77076 31172328 ``` Also , `batch_size=1` I have taken. Regarding number of channels , I am building PSPNet on top of Resnet\_101 , so , I need to take the exact number of channels which Resnet produces , right ? Could you please help me , where can I reduce the number of channels in my code ? Thanks in advance. ---
**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:** [April 20, 2018, 8:32am UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/24 "2018-04-20T08:32:36Z")
As a side note: Try to move the “target fix” to the `Dataset` and remove it from the training loop or alternatively use pure PyTorch code im the training loop. You have 66GB of RAM so a GPU won’t help if you run out of memory on this machine. Do you have the code hosted on GitHub so that I could try to run it? ---
**Author:** ![Shounak\_Kundu](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/a88e4f/32.png) [@Shounak\_Kundu](https://discuss.pytorch.org/u/Shounak_Kundu)\ **Post date:** [April 20, 2018, 10:22am UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/25 "2018-04-20T10:22:27Z")
hi @ptrblck here is the code > I will check the code relocation part and update you. Thanks in advance 🙂 ---
**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:** [April 23, 2018, 10:41am UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/26 "2018-04-23T10:41:08Z")
Sorry for the late reply, I just run it on a machine with 256GB RAM and the forward pass for `batch_size=1` took approx. 53.2 GB. Skimming your code I can’t see anything wrong. Your model just seems to be very big. ---
**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:** [April 23, 2018, 10:50am UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/27 "2018-04-23T10:50:28Z")
[Here](https://github.com/delta-onera/segnet_pytorch) is another implementation of SegNet, which just takes ~1GB for `batch_size=1`. Could you have a look at it and compare both architectures? I’m not familiar with the implementation of SegNet, but there are some differences between your approach and the aforementioned implementation. ---
**Author:** ![Shounak\_Kundu](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/a88e4f/32.png) [@Shounak\_Kundu](https://discuss.pytorch.org/u/Shounak_Kundu)\ **Post date:** [April 23, 2018, 11:03am UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/28 "2018-04-23T11:03:51Z")
Hi , thanks a lot @ptrblck I am using ResNet , even though the question reads “SegNet” ( my bad , I had tried SegNet earlier , later changed on to ResNet) ---
**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:** [April 23, 2018, 11:57am UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/29 "2018-04-23T11:57:14Z")
I dismantled your model and the image size of `[1296, 966]` is just huge. Could you try to cut resize the image and adapt the model to it? Alternatively you could slice the image and use a “windowed” approach. Would this work for you? ---
**Author:** ![Shounak\_Kundu](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/a88e4f/32.png) [@Shounak\_Kundu](https://discuss.pytorch.org/u/Shounak_Kundu)\ **Post date:** [April 23, 2018, 12:08pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/30 "2018-04-23T12:08:29Z")
Slice the image , as in ? ---
**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:** [April 23, 2018, 12:19pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/31 "2018-04-23T12:19:01Z")
The UNet paper used this approach so save memory and use arbitrarily large images. [Figure 2](https://arxiv.org/pdf/1505.04597.pdf) They called it “Overlap-tile strategy”, so sorry for the confusion. I couldn’t find a good name so just used slice. 😉 ---
**Author:** ![Shounak\_Kundu](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/a88e4f/32.png) [@Shounak\_Kundu](https://discuss.pytorch.org/u/Shounak_Kundu)\ **Post date:** [April 23, 2018, 12:39pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/32 "2018-04-23T12:39:26Z")
Hi @ptrblck , thanks a lot… 🙂 ---
**Author:** ![Shounak\_Kundu](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/a88e4f/32.png) [@Shounak\_Kundu](https://discuss.pytorch.org/u/Shounak_Kundu)\ **Post date:** [May 8, 2018, 11:10am UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/33 "2018-05-08T11:10:36Z")
Hi @ptrblck thanks a lot for all the help you did till now. Could you please help me in evaluating in this model ? I am getting ```auto TypeError: Performing basic indexing on a tensor and encountered an error indexing dim 0 with an object of type Variable. The only supported types are integers, slices, numpy scalars, or if indexing with a torch.LongTensor or torch.ByteTensor only a single Tensor may be passed. ``` while converting the label to `color_tranform` Here is full exception stack trace : ```auto size of gray image torch.Size([1, 3, 136, 136]) color_image shape torch.Size([3, 3, 136]) self.cmap shape torch.Size([3, 3]) Mask ==> torch.Size([3, 136, 136]) label ==> 1 --------------------------------------------------------------------------- TypeError Traceback (most recent call last) in () ----> 1 label = color_transform(label) in __call__ (self, gray_image) 43 44 print("Mask ==> ",mask.shape," label ==> ",label) ---> 45 color_image[0][mask] = self.cmap[label][0] 46 color_image[1][mask] = self.cmap[label][1] 47 color_image[2][mask] = self.cmap[label][2] TypeError: Performing basic indexing on a tensor and encountered an error indexing dim 0 with an object of type Variable. The only supported types are integers, slices, numpy scalars, or if indexing with a torch.LongTensor or torch.ByteTensor only a single Tensor may be passed. ``` Here is my code for labelling with different color for semantic segmentation : ```auto def colormap(n): cmap=np.zeros([n, 3]).astype(np.uint8) for i in np.arange(n): r, g, b = np.zeros(3) for j in np.arange(8): r = r + (1<<(7-j))*((i&(1<<(3*j))) >> (3*j)) g = g + (1<<(7-j))*((i&(1<<(3*j+1))) >> (3*j+1)) b = b + (1<<(7-j))*((i&(1<<(3*j+2))) >> (3*j+2)) cmap[i,:] = np.array([r, g, b]) return cmap class Relabel: def __init__ (self, olabel, nlabel): self.olabel = olabel self.nlabel = nlabel def __call__ (self, tensor): assert isinstance(tensor, torch.LongTensor), 'tensor needs to be LongTensor' for i in tensor: i[i == self.olabel] = self.nlabel #print("tensor ",tensor) #print("\n olabel ",self.olabel) #tensor[tensor == self.olabel] = self.nlabel return tensor class ToLabel: def __call__ (self, image): # tensors = [] # for i in image: # tensors.append(torch.from_numpy(np.array(i)).long()) # return tensors return torch.from_numpy(np.array(image)).long().unsqueeze(0) class Colorize: def __init__ (self, n=3): #self.cmap = colormap(256) self.cmap = colormap(136) #self.cmap = colormap(3) self.cmap[n] = self.cmap[-1] self.cmap = torch.from_numpy(self.cmap[:n]) def __call__ (self, gray_image): size = gray_image.size() print("size of gray image ",size) color_image = torch.ByteTensor(3, size[1], size[2]).fill_(0) #color_image = torch.ByteTensor(3, size[0], size[1]).fill_(0) print("color_image shape ",color_image.shape) print("self.cmap shape ",self.cmap.shape) for label in range(1, len(self.cmap)): mask = (label == gray_image[0]).cpu() # mask = gray_image[0] == label # color_image[0][mask] = self.cmap[label][0] # color_image[1][mask] = self.cmap[label][1] # color_image[2][mask] = self.cmap[label][2] print("Mask ==> ",mask," label ==> ",label) color_image[0][mask] = self.cmap[label][0] color_image[1][mask] = self.cmap[label][1] color_image[2][mask] = self.cmap[label][2] return color_image ``` Here is the code for transformation : ```auto color_transform = Colorize() image_transform = ToPILImage() input_transform = Compose([ CenterCrop(256), Scale(136), ToTensor(), Normalize([.485, .456, .406], [.229, .224, .225]), ]) target_transform = Compose([ CenterCrop(256), Scale(136), ToLabel(), Relabel(255, 3), ]) ``` Here is code for model evaluation : ```auto model.eval() image = input_transform(Image.open('dataset-1.0/'+'images/060_resize.png')) label = model(Variable(image, volatile=True).unsqueeze(0)) label = color_transform(label) ``` Could you please 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:** [May 8, 2018, 11:22am UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/34 "2018-05-08T11:22:38Z")
It seems there are some issues regarding the shapes. `color_image` has a shape of `[3, 3, 136]`, which seeme weird. Since the `mask` is `[3, 136, 136]`, I assume the `color_image` should have the same dimensions. Also, it seems you are trying to slice the channels from the `color_image` and apply the `mask` on each slice. If you mask already has 3 channels, you don’t need to do this. Alternatively your mask should only have a width and height. If you would like to assign a value using the mask, you could use `color_image.masked_fill_(mask, value)`. Also, you should update to PyTorch `0.4.0`, since it’s the latest stable release! 😉 ---
**Author:** ![Shounak\_Kundu](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/a88e4f/32.png) [@Shounak\_Kundu](https://discuss.pytorch.org/u/Shounak_Kundu)\ **Post date:** [May 8, 2018, 1:07pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/35 "2018-05-08T13:07:55Z")
hi @ptrblck , thanks for your reply. Actually , I am bit confused . I have some doubts , it would be really great if could address them : 1. My input transformation is of `136` . So , will my `colormap` be of size `136` ? 2. Should I pass `output[0].max(0)[1]` to the `color_transform` function ? What is the advantage of this ? ---
**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:** [May 8, 2018, 1:15pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/36 "2018-05-08T13:15:07Z")
1. I think your `mask` should have the same height and width as the `color_image` it is masking, i.e. `[1, 136, 136]` or `[3, 136, 136]`. This line should most likely be changed: `color_image = torch.ByteTensor(3, size[1], size[2]).fill_(0)` to `color_image = torch.ByteTensor(3, size[2], size[3]).fill_(0)`. 2. I thing it’s alright to pass `label` to `color_transform`. ---
**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:** [May 8, 2018, 1:25pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/37 "2018-05-08T13:25:38Z")
Try out this code: ```auto class Colorize: def __init__ (self, n=3): self.cmap = colormap(136) self.cmap[n] = self.cmap[-1] self.cmap = torch.from_numpy(self.cmap[:n]) def __call__ (self, gray_image): size = gray_image.size() print("size of gray image ",size) color_image = torch.ByteTensor(3, size[2], size[3]).fill_(0) #color_image = torch.ByteTensor(3, size[0], size[1]).fill_(0) print("color_image shape ",color_image.shape) print("self.cmap shape ",self.cmap.shape) for label in range(1, len(self.cmap)): mask = (label == gray_image[0]).cpu() print("Mask ==> ",mask," label ==> ",label) color_image[0].masked_fill_(mask[0], self.cmap[label][0]) color_image[1].masked_fill_(mask[1], self.cmap[label][1]) color_image[2].masked_fill_(mask[2], self.cmap[label][2]) return color_image color_transform = Colorize() x = torch.zeros(1, 3, 24, 24).random_(3) color = color_transform(x) plt.imshow(x[0].numpy().transpose(1, 2, 0)) plt.imshow(color.numpy().transpose(1, 2, 0)) ``` ---
**Author:** ![Shounak\_Kundu](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/a88e4f/32.png) [@Shounak\_Kundu](https://discuss.pytorch.org/u/Shounak_Kundu)\ **Post date:** [May 8, 2018, 3:49pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/39 "2018-05-08T15:49:12Z")
Hi @ptrblck , thanks for your help. The code snippet which you have provided , is working. However , I am still finding it bit difficult to incorporate it in actual code. I will ping you with the issues. Thanks a lot again 🙂 ---
**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:** [May 8, 2018, 3:51pm UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/40 "2018-05-08T15:51:03Z")
If your model output is in this shape `[batch_size, classes, height, width]`, you could do the following: ```auto batch_size, classes, h, w = 10, 3, 24, 24 output = torch.randn(batch_size, classes, h, w) pred = torch.argmax(output, 1) ``` ---
**Author:** ![Shounak\_Kundu](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/s/a88e4f/32.png) [@Shounak\_Kundu](https://discuss.pytorch.org/u/Shounak_Kundu)\ **Post date:** [May 9, 2018, 9:24am UTC](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388/41 "2018-05-09T09:24:57Z")
Hi @ptrblck I used the sample code provided by you. It is working after a minor modification ( changing `mask` to `mask.data` ). But , in output semantic segmented image everything coming as black. Do I need to preprocess the image ? Here are my input labels I am using for training the model : ```auto im_arr = np.array(labels) #print("Labels ==> ",np.unique(np.array(labels))) im_arr[(im_arr==0) | (im_arr==11) | (im_arr==12) | (im_arr==13) | (im_arr==14) | (im_arr==15) | (im_arr==16)]=0 im_arr[(im_arr==17) | (im_arr==18) | (im_arr==19) | (im_arr==20) | (im_arr==21) | (im_arr==22) | (im_arr==23) | (im_arr==24) | (im_arr==25) | (im_arr==28) | (im_arr==29) | (im_arr==30)]=0 im_arr[(im_arr==34)| (im_arr==35) | (im_arr==40) | (im_arr==41)]=2 ``` Update 🙂 Hi , I am classifying the classes as follows : ```auto label_np = label.data.numpy() np.amax(label_np) #3.9837084 np.amin(label_np) # -1.5343161 label_np[label_np<0]=0 label_np[label_np>3]=2 label_np[label_np==0].shape #(29490,) label_np[np.logical_and(label_np>0.6,label_np<=3)]=1 label_np[np.logical_and(label_np>0,label_np<=0.6)]=0 color1 = color_transform(torch.from_numpy(label_np)) temp_image1 = image_transform(color1) temp_image1.save("temp_image_00001.png") ``` Is this is correct approach ? Please help. [Previous page](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388.md?page=1) [Next page](https://discuss.pytorch.org/t/inconsistent-tensor-sizes-at-the-last-layer-of-segnet/16388.md?page=3)