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. What pytorch version are you using? 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 I was showing a friend something and told him to update his extensions, and he got this error. AttributeError: module 'torch.cuda' has no attribute '_UntypedStorage' Accelerated Computing CUDA CUDA Programming and Performance cuda, pytorch Seemed to resolve it for the other people on that thread earlier too. Sorry for late response 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 [pip3] numpy==1.23.4 CUDA runtime version: Could not collect Browse other questions tagged, Where developers & technologists share private knowledge with coworkers, Reach developers & technologists worldwide. You may re-send via your 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_. Easiest way would be just updating PyTorch to 0.4.0 or higher. BTW, I have to close this issue because it's not a problem of this repo. Tried doing this and got another error =P Dreambooth can suck it. By clicking Sign up for GitHub, you agree to our terms of service and CMake version: version 3.22.1 or in your case: 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)] Clang version: Could not collect torch torch.rfft torch.irfft torch.rfft rfft ,torch.irfft irfft PyTorch version: 1.12.1+cu116 Find centralized, trusted content and collaborate around the technologies you use most. didnt work as well. On a machine with PyTorch version: 1.12.1+cu116, running the following code gets error message module 'torch.cuda' has no attribute '_UntypedStorage'. AttributeError: 'datetime' module has no attribute 'strptime', Error: " 'dict' object has no attribute 'iteritems' ". This happened to me too the last dreambooth update made some requirements change that screwed the python environment. 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? Try to transform the numpy array to a tensor before calling tensor.cuda () RuntimeError: Couldn't install torch. 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. 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. I am actually pruning my model using a particular torch library for pruning then this is what happens model structure device = torch.device("cuda 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. What video game is Charlie playing in Poker Face S01E07? Find centralized, trusted content and collaborate around the technologies you use most. . Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] You might need to install the nightly binary, since Autocasting wasnt shipped in 1.5. WebAttributeError: module 'torch' has no attribute 'cuda' Press any key to continue . Im wondering if my cuda setup is problematic? How do/should administrators estimate the cost of producing an online introductory mathematics class? How do I check if an object has an attribute? So I've ditched this extension for now, since I was no longer really using it anyway and updating it regularly breaks my Automatic1111 environment. . and delete current Python and "venv" folder in WebUI's directory. 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. Have a question about this project? CUDA used to build PyTorch: 11.6 profile. See instructions here https://pytorch.org/get-started/locally/ RuntimeError: Error running command. Yesterday I installed Pytorch with "conda install pytorch torchvision -c pytorch". 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. 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) PyTorch - "Attribute Error: module 'torch' has no attribute 'float', How Intuit democratizes AI development across teams through reusability. Otherwise already loaded modules are omitted during import and changes are not applied. prepare_environment() Why does Mister Mxyzptlk need to have a weakness in the comics? To learn more, see our tips on writing great answers. class GradScaler(torch.cuda.amp.GradScaler): AttributeError: module torch.cuda has no attribute amp Environment: GPU : RTX 8000 CUDA: 10.0 Pytorch module 'torch.cuda' has no attribute '_UntypedStorage'. This program is tested with 3.10.6 Python, but you have 3.11.0. Why are Suriname, Belize, and Guinea-Bissau classified as "Small Island Developing States"? Does ZnSO4 + H2 at high pressure reverses to Zn + H2SO4? Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/cu117 To learn more, see our tips on writing great answers. GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3090 please help I just sent the iynb model Very strange. So something is definitely hostile as you said =P. I'm running without dreambooth now as I had to use CPU training anyway with my 4Gb card and they made that harder recently so I'd gone to Colab, which is much quicker anyway. New replies are no longer allowed. I had to delete my venv folder in the end and let automatic1111 rebuild it. Since this issue is not related to Intel Devcloud can we close the case? File "C:\ai\stable-diffusion-webui\launch.py", line 272, in prepare_environment profile. Staging Ground Beta 1 Recap, and Reviewers needed for Beta 2, Calling a function of a module by using its name (a string). You may just comment it out. Can you provide the full error stack trace? Error: " 'dict' object has no attribute 'iteritems' ", Getting Nan result out of ResNet101 backbone with Kitti images. Do you know how I can fix it? --------------------------------------------------------------------------- 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'. [notice] To update, run: C:\ai\stable-diffusion-webui\venv\Scripts\python.exe -m pip install --upgrade pip Connect and share knowledge within a single location that is structured and easy to search. You may just comment it out. 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. I have same error after install pytorch from channel "soumith" with this command: After reinstalling from pytorch channel all works fine. WebAttributeError: module tensorflow has no attribute GPUOptionsTensorflow 1.X 2.XTensorflow 1.Xgpu_options = tf.GPUOptions(per_process_gpu_memory_fraction)Tensorflow 2.Xgpu_options =tf.compat.v1.GPUOptions(per_process_gpu_memory_fractio 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. For more complete information about compiler optimizations, see our Optimization Notice. --------------------------------------------------------------------------- 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'. Follow Up: struct sockaddr storage initialization by network format-string, Full text of the 'Sri Mahalakshmi Dhyanam & Stotram'. You may re-send via your. Already on GitHub? For the Nozomi from Shinagawa to Osaka, say on a Saturday afternoon, would tickets/seats typically be available - or would you need to book? Thanks for your answer. Sign in WebLKML Archive on lore.kernel.org help / color / mirror / Atom feed * [PATCH v38 00/39] LSM: Module stacking for AppArmor [not found] <20220927195421.14713-1-casey.ref@schaufler-ca.com> @ 2022-09-27 19:53 ` Casey Schaufler 2022-09-27 19:53 ` [PATCH v38 01/39] LSM: Identify modules by more than name Casey Schaufler ` (38 more replies) 0 siblings, NVIDIA doesnt develop, maintain, or support pytorch. AC Op-amp integrator with DC Gain Control in LTspice. This is just a side node, because your code and error message do not match: When importing code to Jupyter Notebook it is safest to restart the kernel after doing changes to the imported code. Commit hash: 0cc0ee1 Yes twice updates to dreambooth have screwed my python environment badly. What browsers do you use to Shouldn't this install latest version? Sign in I will spend some more time digging into this but. I read the PyTorch Q&A and there may be some problems about my CUDA, I tried to add --gpu_ids -1 to my code (that is, sh experiments/run_mnist.sh --gpu_ids -1, see the following picture), still exit error. """, 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. Sorry, you must verify to complete this action. I have not tested it on Linux, but I used the command for Windows and it worked great for me on Anaconda. File "C:\ai\stable-diffusion-webui\launch.py", line 89, in run This topic was automatically closed 14 days after the last reply. Python platform: Linux-5.15.0-52-generic-x86_64-with-glibc2.35 This is kind of confusing because the traceback then shows an error which doesn't make sense for the given line. How can I check before my flight that the cloud separation requirements in VFR flight rules are met? How do I check if an object has an attribute? Site design / logo 2023 Stack Exchange Inc; user contributions licensed under CC BY-SA. Site design / logo 2023 Stack Exchange Inc; user contributions licensed under CC BY-SA. How to handle a hobby that makes income in US, Linear Algebra - Linear transformation question. . [Bug]: AttributeError: module 'torch' has no attribute 'cuda', https://www.python.org/downloads/release/python-3109/, https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases. So for example when changing in the imported code: torch.tensor([1, 0, 0, 0, 1, 0], dtype=torch.float) to torch.FloatTensor([1,0,0,0,1,0]) it might still complain about torch.float even if the line then doesn't contain a torch.floatanymore (it even shows the new code in the traceback). NVIDIA most definitely does have a PyTorch team, but the PyTorch forums are still a great place to ask questions. raise RuntimeError(f"""{errdesc or 'Error running command'}. Is it suspicious or odd to stand by the gate of a GA airport watching the planes? Why is there a voltage on my HDMI and coaxial cables? ROCM used to build PyTorch: N/A, OS: Ubuntu 22.04.1 LTS (x86_64) If you encounter an error with "RuntimeError: Couldn't install torch." # Note: the code can run if the following two lines are commented out. You may try updating. or any other error regarding unsuccessful package (library) installation, If you don't want to update or if you are not able to do so for some reason. By clicking Accept all cookies, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy. In torch.distributed, how to average gradients on different GPUs correctly? By clicking Post Your Answer, you agree to our terms of service, privacy policy and cookie policy. Sign up for a free GitHub account to open an issue and contact its maintainers and the community. Later in the night i did the same and got the same error. conda list torch gives me: But, when asking for the torchvision version in Jupyter Notebook, I get: AttributeError: module 'torch.fft' has no attribute 'fftfreq' Hot Network Questions Add circled letters in titles ), Implement Seek on /dev/stdin file descriptor in Rust. Asking for help, clarification, or responding to other answers. How can I import a module dynamically given the full path? WebAttributeError: module 'torch' has no attribute 'cuda' Press any key to continue . 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. Why do we calculate the second half of frequencies in DFT? However, the code that works in Ubuntu 20.04, throws this error: I have this version of PyTorch on Ubuntu 20.04: Ideally I want the same code to run across two machines. Can I tell police to wait and call a lawyer when served with a search warrant? cuDNN version: Could not collect Staging Ground Beta 1 Recap, and Reviewers needed for Beta 2, Python error "ImportError: No module named". File "C:\ai\stable-diffusion-webui\launch.py", line 269, in prepare_environment Is CUDA available: True i actually reported that to dreambooth extension author 3 weeks ago and got told off. With the more extensive dataset, I receive the AttributeError in the subject header and RuntimeError: Pin memory threat exited unexpectedly after 8 iterations. File "C:\ai\stable-diffusion-webui\launch.py", line 105, in run Why does it seem like I am losing IP addresses after subnetting with the subnet mask of 255.255.255.192/26? This is the first time for me to run Pytorch with GPU on a linux machine. privacy statement. message, What is the difference between paper presentation and poster presentation? Press any key to continue . Please click the verification link in your email. Can carbocations exist in a nonpolar solvent? Normal boot up. (Initially, I also got the same error, that was before following this). As the PyTorch forum member with the most posts manages the PyTorch Core team @ NVIDIA. 0cc0ee1. The latter error is associated with the pytorch dataloader, but all suggested solutions say to update to pytorch >= 1.7, which I have. Browse other questions tagged, Where developers & technologists share private knowledge with coworkers, Reach developers & technologists worldwide. Hi, Could you give us an update? This is more of a comment then an answer. AttributeError: 'module' object has no attribute 'urlopen'. Why do I get AttributeError: 'NoneType' object has no attribute 'something'? Making statements based on opinion; back them up with references or personal experience. Since this issue is not related to Intel Devcloud can we close the case? Nvidia driver version: 510.47.03 At this moment we are not planning to move to pytorch 1.13 yet. We are closing the case assuming that your issue got resolved.Please raise a new thread in case of any further issues. How would "dark matter", subject only to gravity, behave? File "C:\ai\stable-diffusion-webui\launch.py", line 360, in Did any DOS compatibility layers exist for any UNIX-like systems before DOS started to become outmoded? 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. ERROR: Could not find a version that satisfies the requirement torch==1.13.1+cu117 (from versions: none) How can we prove that the supernatural or paranormal doesn't exist? Asking for help, clarification, or responding to other answers. 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 The text was updated successfully, but these errors were encountered: torch cannot detect cuda anymore, most likely you'll need to reinstall torch. Asking for help, clarification, or responding to other answers. By clicking Post Your Answer, you agree to our terms of service, privacy policy and cookie policy. What is the purpose of non-series Shimano components? Edit: running the same script with the less extensive dataset also produces the AttributeError in the subject. privacy statement. However, the error disappears if not using cuda. Please see. Still get this error--module 'torch._C' has no attribute '_cuda_setDevice', https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/360, https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/67, https://github.com/samet-akcay/ganomaly/blob/master/options.py#L40, module 'torch._C' has no attribute '_cuda_setDevice', AttributeError: module 'torch._C' has no attribute '_cuda_setDevice'. Are there tables of wastage rates for different fruit and veg? Difference between "select-editor" and "update-alternatives --config editor". Thanks for contributing an answer to Stack Overflow! Thank you. Is it possible to rotate a window 90 degrees if it has the same length and width? By clicking Accept all cookies, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy. WebThis package adds support for CUDA tensor types, that implement the same function as CPU tensors, but they utilize GPUs for computation. [notice] A new release of pip available: 22.3 -> 23.0.1 [pip3] torchaudio==0.12.1+cu116 To subscribe to this RSS feed, copy and paste this URL into your RSS reader. or can I please get some context of why this is occuring? We tried running your code.The issue seems to be with the quantized.Conv3d, instead you can use normal convolution3d. vegan) just to try it, does this inconvenience the caterers and staff? Just renamed it to something else and delete the file named 'torch.py' in the directory Be sure to install PyTorch with CUDA support. 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? As you did not include a full error traceback I can only conjecture what the problem is. Not the answer you're looking for? The best approach would be to use the same PyTorch release on both machines. 3cuda 4killpidnvidia-smigpu 5pytorch pytorchcuda torch : 1.12.1/ python: 3.7.6 / cuda : What is the purpose of this D-shaped ring at the base of the tongue on my hiking boots? ERROR: No matching distribution found for torch==1.13.1+cu117. File "C:\ai\stable-diffusion-webui\launch.py", line 129, in run_python As you can see, the command you used to install pytorch is different from the one here. Why is this sentence from The Great Gatsby grammatical? I could fix this on the 1.12 branch, but will there be a 1.12.2 release? Well occasionally send you account related emails. to your account. How can I import a module dynamically given the full path? To subscribe to this RSS feed, copy and paste this URL into your RSS reader. So if there was an error in the old code this error might still occur and the traceback then points to the line you have just corrected. stderr: Traceback (most recent call last): privacy statement. Making statements based on opinion; back them up with references or personal experience. . Already on GitHub? Have a question about this project? Is there a single-word adjective for "having exceptionally strong moral principles"? The text was updated successfully, but these errors were encountered: I don't think the function torch._C._cuda_setDevice or torch.cuda.set_device is available in a cpu-only build. If you sign in, click, Sorry, you must verify to complete this action. Is debug build: False Traceback (most recent call last): Please click the verification link in your email. Is there a single-word adjective for "having exceptionally strong moral principles"? You might want to ask pytorch questions on a pytorch forum. """, 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.