when i run the script feat_extract.py,i got this error,why?
fast_input shape: (1, 3, 18, 224, 224)
slow_input shape: (1, 3, 0, 224, 224)
Fast x shape: (1, 8, 18, 112, 112)
[13:23:12] ../src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (set the environment variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable)
Traceback (most recent call last):
File "feat_extract.py", line 215, in
main(logger)
File "feat_extract.py", line 199, in main
video_feat = net(video_input.astype(opt.dtype, copy=False))
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/gluon/block.py", line 682, in call
out = self.forward(args)
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/gluon/block.py", line 1309, in forward
return self.hybrid_forward(ndarray, x, args, params)
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/gluoncv/model_zoo/action_recognition/slowfast.py", line 364, in hybrid_forward
slow = self.SlowPath(F, slow_input, lateral)
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/gluoncv/model_zoo/action_recognition/slowfast.py", line 380, in SlowPath
x = self.slow_conv1(x) # bx64x4x112x112, input is bx3x4x224x224
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/gluon/block.py", line 682, in call
out = self.forward(args)
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/gluon/block.py", line 1309, in forward
return self.hybrid_forward(ndarray, x, args, params)
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/gluon/nn/conv_layers.py", line 145, in hybrid_forward
act = getattr(F, self._op_name)(x, weight, name='fwd', **self._kwargs)
File "", line 169, in Convolution
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/_ctypes/ndarray.py", line 91, in _imperative_invoke
ctypes.byref(out_stypes)))
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/base.py", line 246, in check_call
raise get_last_ffi_error()
mxnet.base.MXNetError: Traceback (most recent call last):
File "../include/mxnet/./tuple.h", line 544
MXNetError: Check failed: dim_size_is_known(d[i]): Shape dim size must be known, while received -1
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
when i run the script feat_extract.py,i got this error,why? fast_input shape: (1, 3, 18, 224, 224) slow_input shape: (1, 3, 0, 224, 224) Fast x shape: (1, 8, 18, 112, 112) [13:23:12] ../src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (set the environment variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable) Traceback (most recent call last): File "feat_extract.py", line 215, in
main(logger)
File "feat_extract.py", line 199, in main
video_feat = net(video_input.astype(opt.dtype, copy=False))
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/gluon/block.py", line 682, in call
out = self.forward(args)
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/gluon/block.py", line 1309, in forward
return self.hybrid_forward(ndarray, x, args, params)
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/gluoncv/model_zoo/action_recognition/slowfast.py", line 364, in hybrid_forward
slow = self.SlowPath(F, slow_input, lateral)
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/gluoncv/model_zoo/action_recognition/slowfast.py", line 380, in SlowPath
x = self.slow_conv1(x) # bx64x4x112x112, input is bx3x4x224x224
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/gluon/block.py", line 682, in call
out = self.forward(args)
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/gluon/block.py", line 1309, in forward
return self.hybrid_forward(ndarray, x, args, params)
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/gluon/nn/conv_layers.py", line 145, in hybrid_forward
act = getattr(F, self._op_name)(x, weight, name='fwd', **self._kwargs)
File "", line 169, in Convolution
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/_ctypes/ndarray.py", line 91, in _imperative_invoke
ctypes.byref(out_stypes)))
File "/opt/conda/envs/torch6/lib/python3.7/site-packages/mxnet/base.py", line 246, in check_call
raise get_last_ffi_error()
mxnet.base.MXNetError: Traceback (most recent call last):
File "../include/mxnet/./tuple.h", line 544
MXNetError: Check failed: dim_size_is_known(d[i]): Shape dim size must be known, while received -1