Why does it seem like I am losing IP addresses after subnetting with the subnet mask of 255.255.255.192/26? Does ZnSO4 + H2 at high pressure reverses to Zn + H2SO4? In the __init__.py of the module named torch-sparse, it is so bizarre and confusing .And torch.__version__ == 1.8.0 , torch-sparse == 0.6.11. Commit hash: 0cc0ee1 GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3090 What does the "yield" keyword do in Python? Module Browse other questions tagged, Where developers & technologists share private knowledge with coworkers, Reach developers & technologists worldwide. The name of the source file was 'torch.py'. Traceback (most recent call last): update some extensions, and when I restarted stable. PyTorch version: 1.12.1+cu116 run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True) Webimport torch.nn.utils.prune as prune device = torch.device("cuda" if torch.cuda.is_available() else "cpu") model = C3D(num_classes=2).to(device=device) update some extensions, and when I restarted stable. On a machine with PyTorch version: 1.12.1+cu116, running the following code gets error message module 'torch.cuda' has no attribute '_UntypedStorage'. Is there a workaround? Traceback (most recent call last): File "D:/anaconda/envs/ml/Lib/site-packages/torch_sparse/__init__.py", line 4, in import torch File "D:\anaconda\envs\ml\lib\site-packages\torch_, File "D:\anaconda\envs\ml\lib\platform.py", line 897, in system return uname().system File "D:\anaconda\envs\ml\lib\platform.py", line 785, in uname node = _node() File "D:\anaconda\envs\ml\lib\platform.py", line 588, in _node import socket File "D:\anaconda\envs\ml\lib\socket.py", line 52, in import os, sys, io, selectors, File "D:\anaconda\envs\ml\lib\selectors.py", line 12, in import select File "D:\anaconda\envs\ml\Lib\site-packages\torch_sparse\select.py", line 1, in from torch_sparse.tensor import SparseTensor File "D:\anaconda\envs\ml\lib\site-packages\torch_sparse_. You signed in with another tab or window. Please put it in a comment as you might get down-voted, AttributeError: module 'torch' has no attribute 'device', https://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html, How Intuit democratizes AI development across teams through reusability. New replies are no longer allowed. You just need to find the python AttributeError: 'module' object has no attribute 'dumps' By clicking Post Your Answer, you agree to our terms of service, privacy policy and cookie policy. Why does Mister Mxyzptlk need to have a weakness in the comics? How to fix "Attempted relative import in non-package" even with __init__.py, Equation alignment in aligned environment not working properly, Trying to understand how to get this basic Fourier Series. Connect and share knowledge within a single location that is structured and easy to search. You may just comment it out. AttributeError: module torch has no attribute irfft rfft Well occasionally send you account related emails. To learn more, see our tips on writing great answers. To subscribe to this RSS feed, copy and paste this URL into your RSS reader. Seemed to resolve it for the other people on that thread earlier too. If you preorder a special airline meal (e.g. torch cannot detect cuda anymore, most likely you'll need to reinstall torch. You may re-send via your @harshit_k I added more information and you can see that the 0.1.12 is installed. Does your environment recognize torch.cuda? AttributeError: module torch.cuda has no attribute amp Is there a single-word adjective for "having exceptionally strong moral principles"? i actually reported that to dreambooth extension author 3 weeks ago and got told off. So probably you either have somewhere used torch.float in your code or you have imported some code with torch.float. See instructions here https://pytorch.org/get-started/locally/ Connect and share knowledge within a single location that is structured and easy to search. Have you installed the CUDA version of pytorch? We tried running your code.The issue seems to be with the quantized.Conv3d, instead you can use normal convolution3d. I'm trying to implement the Spatial Transformer Network from here and I am running into this issue: This AttributeError implies that somewhere in the code must be something like torch.float. I have two machines that I need to check my code across one is Ubuntu 18.04 and the other is Ubuntu 20.04. How do I check if an object has an attribute? The error is unfortunately not super descriptive or guiding me how to fix it. Sorry, you must verify to complete this action. stderr: Traceback (most recent call last): if update to an extension did this, please let us know - in my book, that kind of behavior is borderline hostile as extension should NOT change core libraries, only libraries that are extra for that extension. Why do many companies reject expired SSL certificates as bugs in bug bounties? d8ahazard/sd_dreambooth_extension#931. Thanks for your answer. I'm using Windows, conda environment, installed Pytorch-1.7.1, Torchvision-0.8.2, Cuda-Toolkit-11.0 > all compatible. To learn more, see our tips on writing great answers. Python platform: Linux-5.15.0-52-generic-x86_64-with-glibc2.35 Sign up for a free GitHub account to open an issue and contact its maintainers and the community. Help for those needing help starting or connecting to the Intel DevCloud, The Intel sign-in experience has changed to support enhanced security controls. (Initially, I also got the same error, that was before following this). Please see. Sorry for late response Windows. Easiest way would be just updating PyTorch to 0.4.0 or higher. The text was updated successfully, but these errors were encountered: This problem doesn't exist in the newer pytorch 1.13. . I ran into this problem as well. This 100% happened after an extension update. Please always post the full error traceback. What is the difference between paper presentation and poster presentation? AttributeError: module 'torch.cuda' has no attribute 'amp' braindotai April 13, 2020, 5:32pm #1 Im running from torch.cuda.amp import GradScaler, autocast and What platforms do you use to access the UI ? NVIDIA doesnt develop, maintain, or support pytorch. I was showing a friend something and told him to update his extensions, and he got this error. Is CUDA available: True CUDA_MODULE_LOADING set to: For more complete information about compiler optimizations, see our Optimization Notice. By clicking Post Your Answer, you agree to our terms of service, privacy policy and cookie policy. Can I tell police to wait and call a lawyer when served with a search warrant? I am actually pruning my model using a particular torch library for pruning, device = torch.device("cuda" if torch.cuda.is_available() else "cpu")class C3D(nn.Module): """ The C3D network. By clicking Accept all cookies, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy. NVIDIA most definitely does have a PyTorch team, but the PyTorch forums are still a great place to ask questions. AttributeError: module 'torch' has no attribute 'cuda', update some extensions, and when I restarted stable. Is XNNPACK available: True, Versions of relevant libraries: Im running from torch.cuda.amp import GradScaler, autocast and got the error as in title. prune.global_unstructured when I use prune.global_unstructure I get that error please help """, def __init__(self, num_classes, pretrained=False): super(C3D, self).__init__() self.conv1 = nn.quantized.Conv3d(3, 64, kernel_size=(3, 3, 3), padding=(1, 1, 1))#..54.14ms self.pool1 = nn.MaxPool3d(kernel_size=(1, 2, 2), stride=(1, 2, 2)), self.conv2 = nn.quantized.Conv3d(64, 128, kernel_size=(3, 3, 3), padding=(1, 1, 1))#**395.749ms** self.pool2 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2)), self.conv3a = nn.quantized.Conv3d(128, 256, kernel_size=(3, 3, 3), padding=(1, 1, 1))#..208.237ms self.conv3b = nn.quantized.Conv3d(256, 256, kernel_size=(3, 3, 3), padding=(1, 1, 1))#***..348.491ms*** self.pool3 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2)), self.conv4a = nn.quantized.Conv3d(256, 512, kernel_size=(3, 3, 3), padding=(1, 1, 1))#..64.714ms self.conv4b = nn.quantized.Conv3d(512, 512, kernel_size=(3, 3, 3), padding=(1, 1, 1))#..169.855ms self.pool4 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2)), self.conv5a = nn.quantized.Conv3d(512, 512, kernel_size=(3, 3, 3), padding=(1, 1, 1))#.27.173ms self.conv5b = nn.quantized.Conv3d(512, 512, kernel_size=(3, 3, 3), padding=(1, 1, 1))#.25.972ms self.pool5 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2), padding=(0, 1, 1)), self.fc6 = nn.Linear(8192, 4096)#21.852ms self.fc7 = nn.Linear(4096, 4096)#.10.288ms self.fc8 = nn.Linear(4096, num_classes)#0.023ms, self.relu = nn.ReLU() self.softmax = nn.Softmax(dim=1), x = self.relu(self.conv1(x)) x = least_squares(self.pool1(x)), x = self.relu(self.conv2(x)) x = least_squares(self.pool2(x)), x = self.relu(self.conv3a(x)) x = self.relu(self.conv3b(x)) x = least_squares(self.pool3(x)), x = self.relu(self.conv4a(x)) x = self.relu(self.conv4b(x)) x = least_squares(self.pool4(x)), x = self.relu(self.conv5a(x)) x = self.relu(self.conv5b(x)) x = least_squares(self.pool5(x)), x = x.view(-1, 8192) x = self.relu(self.fc6(x)) x = self.dropout(x) x = self.relu(self.fc7(x)) x = self.dropout(x), def __init_weight(self): for m in self.modules(): if isinstance(m, nn.Conv3d): init.xavier_normal_(m.weight.data) init.constant_(m.bias.data, 0.01) elif isinstance(m, nn.Linear): init.xavier_normal_(m.weight.data) init.constant_(m.bias.data, 0.01), import torch.nn.utils.prune as prunedevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")model = C3D(num_classes=2).to(device=device)prune.random_unstructured(module, name="weight", amount=0.3), parameters_to_prune = ( (model.conv2, 'weight'), (model.conv3a, 'weight'), (model.conv3b, 'weight'), (model.conv4a, 'weight'), (model.conv4b, 'weight'), (model.conv5a, 'weight'), (model.conv5b, 'weight'), (model.fc6, 'weight'), (model.fc7, 'weight'), (model.fc8, 'weight'),), prune.global_unstructured( parameters_to_prune, pruning_method=prune.L1Unstructured, amount=0.2), --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 19 parameters_to_prune, 20 pruning_method=prune.L1Unstructured, ---> 21 amount=0.2 22 ) ~/.local/lib/python3.7/site-packages/torch/nn/utils/prune.py in global_unstructured(parameters, pruning_method, **kwargs) 1017 1018 # flatten parameter values to consider them all at once in global pruning -> 1019 t = torch.nn.utils.parameters_to_vector([getattr(*p) for p in parameters]) 1020 # similarly, flatten the masks (if they exist), or use a flattened vector 1021 # of 1s of the same dimensions as t ~/.local/lib/python3.7/site-packages/torch/nn/utils/convert_parameters.py in parameters_to_vector(parameters) 18 for param in parameters: 19 # Ensure the parameters are located in the same device ---> 20 param_device = _check_param_device(param, param_device) 21 22 vec.append(param.view(-1)) ~/.local/lib/python3.7/site-packages/torch/nn/utils/convert_parameters.py in _check_param_device(param, old_param_device) 71 # Meet the first parameter 72 if old_param_device is None: ---> 73 old_param_device = param.get_device() if param.is_cuda else -1 74 else: 75 warn = False AttributeError: 'function' object has no attribute 'is_cuda', prune.global_unstructured when I use prune.global_unstructure I get that error. Why is this sentence from The Great Gatsby grammatical? I was stucked by this problem by few days and I hope someone could help me. I'm stuck with this issue and the problem is I cannot use the latest version of pytorch (currently using 1.12+cu11.3). torch.cuda.amp is available in the nightly binaries, so you would have to update. What's the difference between a Python module and a Python package? and delete current Python and "venv" folder in WebUI's directory. File "C:\ai\stable-diffusion-webui\launch.py", line 129, in run_python or can I please get some context of why this is occuring? Thanks for contributing an answer to Stack Overflow! In my code below, I added this statement: device = torch.device ("cuda:0" if torch.cuda.is_available () else "cpu") net.to (device) But this seems not right or enough. What should have happened? PyTorch - "Attribute Error: module 'torch' has no attribute 'float' Is there a single-word adjective for "having exceptionally strong moral principles"? 3cuda 4killpidnvidia-smigpu 5pytorch pytorchcuda torch : 1.12.1/ python: 3.7.6 / cuda : How do/should administrators estimate the cost of producing an online introductory mathematics class? Recovering from a blunder I made while emailing a professor, Linear regulator thermal information missing in datasheet, How to handle a hobby that makes income in US, Minimising the environmental effects of my dyson brain. What is the purpose of this D-shaped ring at the base of the tongue on my hiking boots? How to parse XML and get instances of a particular node attribute? For the code you've posted it makes no sense. It seems that you need to add --device cpu in the command line to make it work. --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 1 get_ipython().system('pip3 install torch==1.2.0+cu92 torchvision==0.4.0+cu92 -f https://download.pytorch.org/whl/torch_stable.html') ----> 2 torch.is_cuda AttributeError: module 'torch' has no attribute 'is_cuda'. By clicking Accept all cookies, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy. ROCM used to build PyTorch: N/A, OS: Ubuntu 22.04.1 LTS (x86_64) AttributeError: module 'torch.cuda' has no attribtue 'amp' #1260 with torch.autocast ('cuda'): AttributeError: module 'torch' has no attribute 'autocast' I have this version of PyTorch on Ubuntu 20.04: python Python 3.8.10 (default, ERROR: No matching distribution found for torch==1.13.1+cu117. Powered by Discourse, best viewed with JavaScript enabled, AttributeError: module 'torch.cuda' has no attribute '_UntypedStorage'. You signed in with another tab or window. module 'torch.cuda' has no attribute '_UntypedStorage' #88839 WebAttributeError: module 'torch' has no attribute 'cuda' Press any key to continue . Otherwise already loaded modules are omitted during import and changes are not applied. PyTorch - "Attribute Error: module 'torch' has no attribute 'float', How Intuit democratizes AI development across teams through reusability. please help I just sent the iynb model How can I import a module dynamically given the full path? I have same error after install pytorch from channel "soumith" with this command: After reinstalling from pytorch channel all works fine. @emailweixu please reopen if error repros on pytorch 1.13. If thats not possible, and assuming you are using the GPU, use torch.cuda.amp.autocast. module If you sign in, click, Sorry, you must verify to complete this action. didnt work as well. stdout: It is lazily initialized, so you can Making statements based on opinion; back them up with references or personal experience. However, the link you referenced for the code contains the following line: PyTorch data types like torch.float came with PyTorch 0.4.0, so when you use something like torch.float in earlier versions like 0.3.1 you will see this error, because torch then actually has no attribute float. To figure out the exact issue we need yourcode and steps to test from our end.Could you sharethe entire code and steps in a zip file? This is kind of confusing because the traceback then shows an error which doesn't make sense for the given line. Powered by Discourse, best viewed with JavaScript enabled, AttributeError: module 'torch.cuda' has no attribute 'amp'. module 'torch' has no attribute 'cuda Sorry, you must verify to complete this action. How do I check if an object has an attribute? If you preorder a special airline meal (e.g. Follow Up: struct sockaddr storage initialization by network format-string, Full text of the 'Sri Mahalakshmi Dhyanam & Stotram'. The same code can run correctly on a different machine with PyTorch version: 1.8.2+cu111, Collecting environment information BTW, I have to close this issue because it's not a problem of this repo. Just renamed it to something else and delete the file named 'torch.py' in the directory to your account, Everything was working well, I then proceeded to update some extensions, and when i restarted stable, I got this error message, Already up to date. Find centralized, trusted content and collaborate around the technologies you use most. File "C:\ai\stable-diffusion-webui\launch.py", line 89, in run Is debug build: False You may re-send via your So something is definitely hostile as you said =P. The best approach would be to use the same PyTorch release on both machines. AttributeError: module 'torch.cuda' has no attribute 'amp' raise RuntimeError(message) raise RuntimeError(f"""{errdesc or 'Error running command'}. Staging Ground Beta 1 Recap, and Reviewers needed for Beta 2, Python error "ImportError: No module named". Already on GitHub? microsoft/Bringing-Old-Photos-Back-to-Life#100. I don't think the function torch._C._cuda_setDevice or torch.cuda.set_device is available in a cpu-only build. How would "dark matter", subject only to gravity, behave? Since this issue is not related to Intel Devcloud can we close the case? Please click the verification link in your email. You may re-send via your, AttributeError: module 'torch' has no attribute 'is_cuda', Intel Connectivity Research Program (Private), oneAPI Registration, Download, Licensing and Installation, Intel Trusted Execution Technology (Intel TXT), Intel QuickAssist Technology (Intel QAT), Gaming on Intel Processors with Intel Graphics. ERROR: Could not find a version that satisfies the requirement torch==1.13.1+cu117 (from versions: none) Installing torch and torchvision How to handle a hobby that makes income in US, Linear Algebra - Linear transformation question. Batch split images vertically in half, sequentially numbering the output files, Euler: A baby on his lap, a cat on his back thats how he wrote his immortal works (origin? You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3109/, Alternatively, use a binary release of WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases, Python 3.11.0 (main, Oct 24 2022, 18:26:48) [MSC v.1933 64 bit (AMD64)] Find centralized, trusted content and collaborate around the technologies you use most. privacy statement. Since this issue is not related to Intel Devcloud can we close the case? CUDA The latter error is associated with the pytorch dataloader, but all suggested solutions say to update to pytorch >= 1.7, which I have. Site design / logo 2023 Stack Exchange Inc; user contributions licensed under CC BY-SA. Re:AttributeError: module 'torch' has no attribute AttributeError: module 'torch' has no attribute 'is_cuda', Intel Connectivity Research Program (Private), oneAPI Registration, Download, Licensing and Installation, Intel Trusted Execution Technology (Intel TXT), Intel QuickAssist Technology (Intel QAT), Gaming on Intel Processors with Intel Graphics. AttributeError:partially initialized module 'torch' has no attribute 'cuda' Ask Question Asked Viewed 894 times 0 In the __init__.py of the module named torch First of all usetorch.cuda.is_available() to detemine the CUDA availability also weneed more details tofigure out the issue.Could you provide us the commands and stepsyou followed? Please click the verification link in your email. Please click the verification link in your email. I am actually pruning my model using a particular torch library for pruning then this is what happens model structure device = torch.device("cuda Yesterday I installed Pytorch with "conda install pytorch torchvision -c pytorch". This is the first time for me to run Pytorch with GPU on a linux machine. By clicking Sign up for GitHub, you agree to our terms of service and cuDNN version: Could not collect Making statements based on opinion; back them up with references or personal experience. Try to transform the numpy array to a tensor before calling tensor.cuda () We tried running your code.The issue seems to be with the quantized.Conv3d, instead you can use normal convolution3d. AttributeError: module 'torch' has no attribute 'is_cuda' What torch torch.rfft torch.irfft torch.rfft rfft ,torch.irfft irfft What browsers do you use to Press any key to continue . [conda] Could not collect. AttributeError: module 'torch' has no attribute 'device' AttributeError: module 'torch' has no attribute 'is_cuda' --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 1 get_ipython().system('pip3 install torch==1.2.0+cu92 torchvision==0.4.0+cu92 -f https://download.pytorch.org/whl/torch_stable.html') ----> 2 torch.is_cuda AttributeError: module 'torch' has no attribute 'is_cuda'. module AC Op-amp integrator with DC Gain Control in LTspice. If you are wondering whether you have a proper CUDA setup, that question belongs on the CUDA setup forum, and the verification steps are provided in the CUDA linux install guide. Similarly to the line you posted in your question. However, the error disappears if not using cuda. This is more of a comment then an answer. CUDA used to build PyTorch: 11.6 vegan) just to try it, does this inconvenience the caterers and staff? Asking for help, clarification, or responding to other answers. WebThis package adds support for CUDA tensor types, that implement the same function as CPU tensors, but they utilize GPUs for computation. Sign up for a free GitHub account to open an issue and contact its maintainers and the community. [pip3] torchvision==0.13.1+cu116 torch.cuda.amptorch1.6torch1.4 1.7.1 I just checked that, it's strange it's 0.1.12_1. Why does Mister Mxyzptlk need to have a weakness in the comics? Sign up for a free GitHub account to open an issue and contact its maintainers and the community. venv "C:\ai\stable-diffusion-webui\venv\Scripts\Python.exe" CUDA runtime version: Could not collect Already on GitHub? Whats the grammar of "For those whose stories they are"? rev2023.3.3.43278. I have not tested it on Linux, but I used the command for Windows and it worked great for me on Anaconda. Command: "C:\ai\stable-diffusion-webui\venv\Scripts\python.exe" -c "import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'" Hi, Sorry for the late response. We tried running your code.The issue seems to be with the quantized.Conv3d, instead you can use normal convolution You may just comment it out. In torch.distributed, how to average gradients on different GPUs correctly? The nature of simulating nature: A Q&A with IBM Quantum researcher Dr. Jamie We've added a "Necessary cookies only" option to the cookie consent popup. WebAttributeError: module 'torch' has no attribute 'cuda' Press any key to continue . I could fix this on the 1.12 branch, but will there be a 1.12.2 release? Is there a single-word adjective for "having exceptionally strong moral principles"? Do roots of these polynomials approach the negative of the Euler-Mascheroni constant? python AttributeError: 'module' object has no attribute 'dumps' pre_dict = {k: v for k, v in pre_dict.items () if k in model_dict} 1. # Note: the code can run if the following two lines are commented out. I tried to fix this problems by refering https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/360 and https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/67 We are closing the case assuming that your issue got resolved.Please raise a new thread in case of any further issues. To learn more, see our tips on writing great answers. AnacondatorchAttributeError: module 'torch' has no attribute 'irfft'module 'torch' has no attribute 'no_grad' In my case command looks like: But you must obtain package list for yours machine form this site: Also happened to me and dreambooth was one of the ones that updated! [pip3] torch==1.12.1+cu116 """, def __init__(self, num_classes, pretrained=False): super(C3D, self).__init__() self.conv1 = nn.quantized.Conv3d(3, 64, kernel_size=(3, 3, 3), padding=(1, 1, 1))#..54.14ms self.pool1 = nn.MaxPool3d(kernel_size=(1, 2, 2), stride=(1, 2, 2)), self.conv2 = nn.quantized.Conv3d(64, 128, kernel_size=(3, 3, 3), padding=(1, 1, 1))#**395.749ms** self.pool2 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2)), self.conv3a = nn.quantized.Conv3d(128, 256, kernel_size=(3, 3, 3), padding=(1, 1, 1))#..208.237ms self.conv3b = nn.quantized.Conv3d(256, 256, kernel_size=(3, 3, 3), padding=(1, 1, 1))#***..348.491ms*** self.pool3 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2)), self.conv4a = nn.quantized.Conv3d(256, 512, kernel_size=(3, 3, 3), padding=(1, 1, 1))#..64.714ms self.conv4b = nn.quantized.Conv3d(512, 512, kernel_size=(3, 3, 3), padding=(1, 1, 1))#..169.855ms self.pool4 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2)), self.conv5a = nn.quantized.Conv3d(512, 512, kernel_size=(3, 3, 3), padding=(1, 1, 1))#.27.173ms self.conv5b = nn.quantized.Conv3d(512, 512, kernel_size=(3, 3, 3), padding=(1, 1, 1))#.25.972ms self.pool5 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2), padding=(0, 1, 1)), self.fc6 = nn.Linear(8192, 4096)#21.852ms self.fc7 = nn.Linear(4096, 4096)#.10.288ms self.fc8 = nn.Linear(4096, num_classes)#0.023ms, self.relu = nn.ReLU() self.softmax = nn.Softmax(dim=1), x = self.relu(self.conv1(x)) x = least_squares(self.pool1(x)), x = self.relu(self.conv2(x)) x = least_squares(self.pool2(x)), x = self.relu(self.conv3a(x)) x = self.relu(self.conv3b(x)) x = least_squares(self.pool3(x)), x = self.relu(self.conv4a(x)) x = self.relu(self.conv4b(x)) x = least_squares(self.pool4(x)), x = self.relu(self.conv5a(x)) x = self.relu(self.conv5b(x)) x = least_squares(self.pool5(x)), x = x.view(-1, 8192) x = self.relu(self.fc6(x)) x = self.dropout(x) x = self.relu(self.fc7(x)) x = self.dropout(x), def __init_weight(self): for m in self.modules(): if isinstance(m, nn.Conv3d): init.xavier_normal_(m.weight.data) init.constant_(m.bias.data, 0.01) elif isinstance(m, nn.Linear): init.xavier_normal_(m.weight.data) init.constant_(m.bias.data, 0.01), import torch.nn.utils.prune as prunedevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")model = C3D(num_classes=2).to(device=device)prune.random_unstructured(module, name="weight", amount=0.3), parameters_to_prune = ( (model.conv2, 'weight'), (model.conv3a, 'weight'), (model.conv3b, 'weight'), (model.conv4a, 'weight'), (model.conv4b, 'weight'), (model.conv5a, 'weight'), (model.conv5b, 'weight'), (model.fc6, 'weight'), (model.fc7, 'weight'), (model.fc8, 'weight'),), prune.global_unstructured( parameters_to_prune, pruning_method=prune.L1Unstructured, amount=0.2), --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 19 parameters_to_prune, 20 pruning_method=prune.L1Unstructured, ---> 21 amount=0.2 22 ) ~/.local/lib/python3.7/site-packages/torch/nn/utils/prune.py in global_unstructured(parameters, pruning_method, **kwargs) 1017 1018 # flatten parameter values to consider them all at once in global pruning -> 1019 t = torch.nn.utils.parameters_to_vector([getattr(*p) for p in parameters]) 1020 # similarly, flatten the masks (if they exist), or use a flattened vector 1021 # of 1s of the same dimensions as t ~/.local/lib/python3.7/site-packages/torch/nn/utils/convert_parameters.py in parameters_to_vector(parameters) 18 for param in parameters: 19 # Ensure the parameters are located in the same device ---> 20 param_device = _check_param_device(param, param_device) 21 22 vec.append(param.view(-1)) ~/.local/lib/python3.7/site-packages/torch/nn/utils/convert_parameters.py in _check_param_device(param, old_param_device) 71 # Meet the first parameter 72 if old_param_device is None: ---> 73 old_param_device = param.get_device() if param.is_cuda else -1 74 else: 75 warn = False AttributeError: 'function' object has no attribute 'is_cuda', prune.global_unstructured when I use prune.global_unstructure I get that error.