the error when I run the example for the imagenet #544
Comments
Hello, perhaps you know how to download the ImageNet dataset for this program to use? |
Maybe the number of classes in your datasets is not 1000, so you should change it... like this: class TotalModel(nn.Module):
def __init__(self, num_class=1000):
super(TotalModel, self).__init__()
net = resnet50(pretrained=True)
self.div_32 = nn.Sequential(*list(net.children())[:-1])
self.other_layers = nn.Linear(2048, num_class)
def forward(self, in_feat):
in_feat = self.div_32(in_feat)
in_feat = in_feat.view(in_feat.size(0), -1)
in_feat = self.other_layers(in_feat)
return in_feat
if __name__ == '__main__':
in_data = torch.randn(4, 3, 224, 224)
net = TotalModel()
out = net(in_data)
print(out.size()) |
|
I have the same issue. Is there anyone who solved this issue? Please help me. |
|
@lartpang seems to have the correct suggestion |
When I tried to run the model for the example/imagenet, I encounter such error.So could you tell me how to solve the problem?
python /home/zrz/code/imagenet_dist/examples-master/imagenet/main.py -a resnet18 -/home/zrz/dataset/imagenet/imagenet2012/ILSVRC2012/raw-data/imagenet-data
=> creating model 'resnet18'
Epoch: [0][ 0/320292] Time 3.459 ( 3.459) Data 0.295 ( 0.295) Loss 7.2399e+00 (7.2399e+00) Acc@1 0.00 ( 0.00) Acc@5 0.00 ( 0.00)
Epoch: [0][ 10/320292] Time 0.043 ( 0.357) Data 0.000 ( 0.027) Loss 9.4861e+00 (1.3169e+01) Acc@1 0.00 ( 0.00) Acc@5 0.00 ( 0.00)
Epoch: [0][ 20/320292] Time 0.046 ( 0.209) Data 0.000 ( 0.014) Loss 7.3722e+00 (1.0817e+01) Acc@1 0.00 ( 0.00) Acc@5 0.00 ( 0.00)
Epoch: [0][ 30/320292] Time 0.032 ( 0.154) Data 0.000 ( 0.010) Loss 6.9166e+00 (9.5394e+00) Acc@1 0.00 ( 0.00) Acc@5 0.00 ( 0.00)
/opt/conda/conda-bld/pytorch_1549630534704/work/aten/src/THCUNN/ClassNLLCriterion.cu:105: void cunn_ClassNLLCriterion_updateOutput_kernel(Dtype *, Dtype *, Dtype *, long *, Dtype *, int, int, int, int, long) [with Dtype = float, Acctype = float]: block: [0,0,0], thread: [3,0,0] Assertion
t >= 0 && t < n_classesfailed.Traceback (most recent call last):
File "/home/zrz/code/imagenet_dist/examples-master/imagenet/main.py", line 417, in
File "/home/zrz/code/imagenet_dist/examples-master/imagenet/main.py", line 113, in main
File "/home/zrz/code/imagenet_dist/examples-master/imagenet/main.py", line 239, in main_worker
File "/home/zrz/code/imagenet_dist/examples-master/imagenet/main.py", line 286, in train
RuntimeError: CUDA error: device-side assert triggered
terminate called after throwing an instance of 'c10::Error'
what(): CUDA error: device-side assert triggered (insert_events at /opt/conda/conda-bld/pytorch_1549630534704/work/aten/src/THC/THCCachingAllocator.cpp:470)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x45 (0x7f099a50acf5 in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libc10.so)
frame #1: + 0x123b8c0 (0x7f099e7ee8c0 in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libcaffe2_gpu.so)
frame #2: at::TensorImpl::release_resources() + 0x50 (0x7f099ac76c30 in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libcaffe2.so)
frame #3: + 0x2a836b (0x7f099818b36b in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libtorch.so.1)
frame #4: + 0x30eff0 (0x7f09981f1ff0 in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libtorch.so.1)
frame #5: torch::autograd::deleteFunction(torch::autograd::Function*) + 0x2f0 (0x7f099818dd70 in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libtorch.so.1)
frame #6: std::_Sp_counted_base<(__gnu_cxx::_Lock_policy)2>::_M_release() + 0x45 (0x7f09c17f87f5 in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #7: torch::autograd::Variable::Impl::release_resources() + 0x4a (0x7f09984001ba in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libtorch.so.1)
frame #8: + 0x12148b (0x7f09c181048b in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #9: + 0x31a49f (0x7f09c1a0949f in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #10: + 0x31a4e1 (0x7f09c1a094e1 in /home/zrz/miniconda3/envs/runze_env_name/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #11: + 0x1993cf (0x5574e4c9a3cf in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #12: + 0xf12b7 (0x5574e4bf22b7 in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #13: + 0xf1147 (0x5574e4bf2147 in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #14: + 0xf115d (0x5574e4bf215d in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #15: + 0xf115d (0x5574e4bf215d in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #16: + 0xf115d (0x5574e4bf215d in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #17: PyDict_SetItem + 0x3da (0x5574e4c37e7a in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #18: PyDict_SetItemString + 0x4f (0x5574e4c4078f in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #19: PyImport_Cleanup + 0x99 (0x5574e4ca4709 in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #20: Py_FinalizeEx + 0x61 (0x5574e4d105f1 in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #21: Py_Main + 0x35e (0x5574e4d1b1fe in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #22: main + 0xee (0x5574e4be402e in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
frame #23: __libc_start_main + 0xf5 (0x7f09d9c2e3d5 in /lib64/libc.so.6)
frame #24: + 0x1c3e0e (0x5574e4cc4e0e in /home/zrz/miniconda3/envs/runze_env_name/bin/python3.6)
The text was updated successfully, but these errors were encountered: