torchdrug
torchdrug copied to clipboard
DeepGraphLearning
ImportError: No module named 'torch_ext'
Hi, I was running the "quickstart" code on my win10. I used torch = 1.8.0 and python = 3.7 with cuda = 10.2.
The problems happened when I tried training the model in Jupyter:
optimizer = torch.optim.Adam(task.parameters(), lr=1e-3)
solver = core.Engine(task, train_set, valid_set, test_set, optimizer, gpus=[0],
batch_size=512) solver.train(num_epoch=100)
And this turned to:
---------------------------------------------------------------------------
ImportError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_19744/1406504193.py in <module>
----> 1 solver.train(num_epoch=100)
d:\conda\envs\torchdrug\lib\site-packages\torchdrug-0.1.0-py3.7.egg\torchdrug\core\engine.py in train(self, num_epoch, batch_per_epoch)
141 batch = utils.cuda(batch, device=self.device)
142
--> 143 loss, metric = model(batch)
144 if not loss.requires_grad:
145 raise RuntimeError("Loss doesn't require grad. Did you define any loss in the task?")
d:\conda\envs\torchdrug\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
d:\conda\envs\torchdrug\lib\site-packages\torchdrug-0.1.0-py3.7.egg\torchdrug\tasks\property_prediction.py in forward(self, batch)
72 metric = {}
73
---> 74 pred = self.predict(batch, all_loss, metric)
75
76 if all([t not in batch for t in self.task]):
d:\conda\envs\torchdrug\lib\site-packages\torchdrug-0.1.0-py3.7.egg\torchdrug\tasks\property_prediction.py in predict(self, batch, all_loss, metric)
103 def predict(self, batch, all_loss=None, metric=None):
104 graph = batch["graph"]
--> 105 output = self.model(graph, graph.node_feature.float(), all_loss=all_loss, metric=metric)
106 pred = self.linear(output["graph_feature"])
107 return pred
d:\conda\envs\torchdrug\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
d:\conda\envs\torchdrug\lib\site-packages\torchdrug-0.1.0-py3.7.egg\torchdrug\models\gin.py in forward(self, graph, input, all_loss, metric)
74
75 for layer in self.layers:
---> 76 hidden = layer(graph, layer_input)
77 if self.short_cut and hidden.shape == layer_input.shape:
78 hidden = hidden + layer_input
d:\conda\envs\torchdrug\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
d:\conda\envs\torchdrug\lib\site-packages\torchdrug-0.1.0-py3.7.egg\torchdrug\layers\conv.py in forward(self, graph, input)
89 update = checkpoint.checkpoint(self._message_and_aggregate, *graph.to_tensors(), input)
90 else:
---> 91 update = self.message_and_aggregate(graph, input)
92 output = self.combine(input, update)
93 return output
d:\conda\envs\torchdrug\lib\site-packages\torchdrug-0.1.0-py3.7.egg\torchdrug\layers\conv.py in message_and_aggregate(self, graph, input)
339 def message_and_aggregate(self, graph, input):
340 adjacency = utils.sparse_coo_tensor(graph.edge_list.t()[:2], graph.edge_weight,
--> 341 (graph.num_node, graph.num_node))
342 update = torch.sparse.mm(adjacency.t(), input)
343 if self.edge_linear:
d:\conda\envs\torchdrug\lib\site-packages\torchdrug-0.1.0-py3.7.egg\torchdrug\utils\torch.py in sparse_coo_tensor(indices, values, size)
160 size (list): size of the tensor
161 """
--> 162 return torch_ext.sparse_coo_tensor_unsafe(indices, values, size)
163
164
d:\conda\envs\torchdrug\lib\site-packages\torchdrug-0.1.0-py3.7.egg\torchdrug\utils\torch.py in __getattr__(self, key)
28 self.module = cpp_extension.load(self.name, self.sources, self.extra_cflags, self.extra_cuda_cflags,
29 self.extra_ldflags, self.extra_include_paths, self.build_directory,
---> 30 self.verbose, **self.kwargs)
31 return getattr(self.module, key)
32
d:\conda\envs\torchdrug\lib\site-packages\torch\utils\cpp_extension.py in load(name, sources, extra_cflags, extra_cuda_cflags, extra_ldflags, extra_include_paths, build_directory, verbose, with_cuda, is_python_module, is_standalone, keep_intermediates)
1089 is_python_module,
1090 is_standalone,
-> 1091 keep_intermediates=keep_intermediates)
1092
1093
d:\conda\envs\torchdrug\lib\site-packages\torch\utils\cpp_extension.py in _jit_compile(name, sources, extra_cflags, extra_cuda_cflags, extra_ldflags, extra_include_paths, build_directory, verbose, with_cuda, is_python_module, is_standalone, keep_intermediates)
1315 return _get_exec_path(name, build_directory)
1316
-> 1317 return _import_module_from_library(name, build_directory, is_python_module)
1318
1319
d:\conda\envs\torchdrug\lib\site-packages\torch\utils\cpp_extension.py in _import_module_from_library(module_name, path, is_python_module)
1697 def _import_module_from_library(module_name, path, is_python_module):
1698 # https://stackoverflow.com/questions/67631/how-to-import-a-module-given-the-full-path
-> 1699 file, path, description = imp.find_module(module_name, [path])
1700 # Close the .so file after load.
1701 with file:
d:\conda\envs\torchdrug\lib\imp.py in find_module(name, path)
294 break # Break out of outer loop when breaking out of inner loop.
295 else:
--> 296 raise ImportError(_ERR_MSG.format(name), name=name)
297
298 encoding = None
ImportError: No module named 'torch_ext'
The same code works well in Colab and I suspect this is because I couldn't install rdkit-pypi and installed rdkit on conda instead.
Thanks for the observation. TorchDrug is mainly developed and tested on Linux, and should work with Colab. Currently there is no guarantee for installing TorchDrug on Windows, but we will come up with Windows support soon.
Hi, I met the same problem when I was running the "quickstart" code on ubunte20.04. I used torch = 1.8.0 and python = 3.8 with cuda = 11.1.
Do you guys install from conda or from source? I just checked the conda package and torch_ext.cpp lies correctly under torchdrug/utils/extension. torch_ext should be automatically imported and JIT compiled by PyTorch when it is used.
One issue I've encountered with PyTorch JIT is that if you kill the process during the compilation of JIT, it sometimes causes a broken compiled binary and JIT can neither load it or recompile it. You need to manually delete the folder torch_extensions, which lies under either /home/your_user_name/.cache or /tmp by default.
Had the same issue, and was able to fix it by:
rm -rf /home/your_user_name/.cache/torch_extensions
Had the same issue, and was able to fix it by:
rm -rf /home/your_user_name/.cache/torch_extensions
If this can solve, I believe it's caused by the broken cache in JIT. This is typically caused by Ctrl-C break during compilation or compiling multiple instances of the same extension at the same time.
If you want to import torchdrug in several processes on the same machine, a safe solution is to manually specify a separate extension directory for each process like
TORCH_EXTENSIONS_DIR=/path/to/your/extensions python script.py
I'm using anaconda on windows and install torchdrug and other required packages in specific environment.
I've got the message : "_ImportError: DLL load failed while importing torch_ext: The specified module could not be found._"
I dont know if it is the same problem as mention above. If yes, there is no solution fo now until windows compatible version release right?
Does it compatible with conda in linux windows subsystem WSL?
@natchanon-me Hi! I am not sure if they are the same problem, but you problem must also be caused by JIT. We didn't test torchdrug on Windows. I think TorchDrug might be compatible with Windows if the JIT utilities (e.g. g++ on Linux. on Windows I guess it's MSVC) from PyTorch work well, since the library doesn't rely on any pre-compiled binaries.
We will test the installation on Windows soon.
@natchanon-me Windows is now supported! Please check https://torchdrug.ai/docs/installation.html#windows-powershell
@natchanon-me Windows is now supported! Please check https://torchdrug.ai/docs/installation.html#windows-powershell
Yeah, I'll try soon. Thanks for great work!!
I am running into a similar issue, CentOS7, python 3.8, pytorch 1.8, cuda 10.1.
Pytorch works so not sure what the compiler warning is from. Another strange point -- I only have issues running torchdrug from the command line, I am able to train a network in a jupyter notebook....
14:20:53 >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
14:20:53 Epoch 0 begin
/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/utils/cpp_extension.py:283: UserWarning:
!! WARNING !!
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
Your compiler (c++) is not compatible with the compiler Pytorch was
built with for this platform, which is g++ on linux. Please
use g++ to to compile your extension. Alternatively, you may
compile PyTorch from source using c++, and then you can also use
c++ to compile your extension.
See https://github.com/pytorch/pytorch/blob/master/CONTRIBUTING.md for help
with compiling PyTorch from source.
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
!! WARNING !!
warnings.warn(WRONG_COMPILER_WARNING.format(
Traceback (most recent call last):
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1667, in _run_ninja_build
subprocess.run(
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/subprocess.py", line 516, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "pretrain_chem.py", line 82, in <module>
sys.exit(main())
File "pretrain_chem.py", line 78, in main
process(args)
File "pretrain_chem.py", line 43, in process
solver.train(num_epoch=5)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/core/engine.py", line 143, in train
loss, metric = model(batch)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/tasks/pretrain.py", line 139, in forward
pred, target = self.predict_and_target(batch, all_loss, metric)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/tasks/pretrain.py", line 118, in predict_and_target
output = self.model(graph, node_feature.float(), all_loss, metric)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/models/gin.py", line 76, in forward
hidden = layer(graph, layer_input)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/layers/conv.py", line 91, in forward
update = self.message_and_aggregate(graph, input)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/layers/conv.py", line 340, in message_and_aggregate
adjacency = utils.sparse_coo_tensor(graph.edge_list.t()[:2], graph.edge_weight,
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/utils/torch.py", line 182, in sparse_coo_tensor
return torch_ext.sparse_coo_tensor_unsafe(indices, values, size)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/utils/torch.py", line 27, in __getattr__
return getattr(self.module, key)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/utils/decorator.py", line 21, in __get__
result = self.func(obj)
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/utils/torch.py", line 31, in module
return cpp_extension.load(self.name, self.sources, self.extra_cflags, self.extra_cuda_cflags,
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1079, in load
return _jit_compile(
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1292, in _jit_compile
_write_ninja_file_and_build_library(
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1404, in _write_ninja_file_and_build_library
_run_ninja_build(
File "/srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1683, in _run_ninja_build
raise RuntimeError(message) from e
RuntimeError: Error building extension 'torch_ext': [1/2] c++ -MMD -MF torch_ext.o.d -DTORCH_EXTENSION_NAME=torch_ext -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/include -isystem /srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/include/TH -isystem /srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/include/THC -isystem /srv/home/wconnell/anaconda3/envs/10-torchdrug/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -Ofast -fopenmp -DAT_PARALLEL_OPENMP -DCUDA_OP -c /srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/utils/extension/torch_ext.cpp -o torch_ext.o
FAILED: torch_ext.o
c++ -MMD -MF torch_ext.o.d -DTORCH_EXTENSION_NAME=torch_ext -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/include -isystem /srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/include/TH -isystem /srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torch/include/THC -isystem /srv/home/wconnell/anaconda3/envs/10-torchdrug/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -Ofast -fopenmp -DAT_PARALLEL_OPENMP -DCUDA_OP -c /srv/home/wconnell/anaconda3/envs/10-torchdrug/lib/python3.8/site-packages/torchdrug/utils/extension/torch_ext.cpp -o torch_ext.o
c++: error: unrecognized command line option ‘-std=c++14’
ninja: build stopped: subcommand failed.
@natchanon-me Windows is now supported! Please check https://torchdrug.ai/docs/installation.html#windows-powershell
What if I am running VSCode and my project is in a conda environment. Which steps are required to get it up and running? I run Python 3.8 rather than the specified 3.7.
