search

princeton-vl / pytorch_stacked_hourglass

Pytorch implementation of the ECCV 2016 paper "Stacked Hourglass Networks for Human Pose Estimation"
BSD 3-Clause "New" or "Revised" License
469 stars 94 forks source link

RunTImeRrror：max_pool2d_with_indices_out_cuda_frame failed with error code 0 #6

Closed GuHuangAI closed 4 years ago

GuHuangAI commented 4 years ago

when i run python train.py -e test_run_001 the error occured: loading data... Done (t=4.74s) epoch: 0 start train test_run_001 0% 0/1000 [00:00<?, ?it/s]Traceback (most recent call last): File "train.py", line 127, in <module> main() File "train.py", line 123, in main train(func, data_func, config) File "train.py", line 94, in train outs = train_func(batch_id + i, config, phase, **datas) File "/content/pytorch_stacked_hourglass/task/pose.py", line 110, in make_train result = net(inputs['imgs'], **{i:inputs[i] for i in inputs if i!='imgs'}) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/content/pytorch_stacked_hourglass/task/pose.py", line 68, in forward combined_hm_preds = self.model(imgs, **inps) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/parallel/data_parallel.py", line 150, in forward return self.module(*inputs[0], **kwargs[0]) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/content/pytorch_stacked_hourglass/models/posenet.py", line 54, in forward hg = self.hgs[i](x) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/container.py", line 100, in forward input = module(input) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/content/pytorch_stacked_hourglass/models/layers.py", line 81, in forward pool1 = self.pool1(x) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/pooling.py", line 141, in forward self.return_indices) File "/usr/local/lib/python3.6/dist-packages/torch/_jit_internal.py", line 181, in fn return if_false(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py", line 488, in _max_pool2d input, kernel_size, stride, padding, dilation, ceil_mode) RuntimeError: max_pool2d_with_indices_out_cuda_frame failed with error code 0 could you give me some help?

GuHuangAI commented 4 years ago

i've solved it. the reason is that the version of my pytorch is 1.3.0. just uninstall is and install 1.0.0.