search

kenziyuliu / DGNN-PyTorch

Unofficial PyTorch implementation of the CVPR'19 paper "Skeleton-Based Action Recognition with Directed Graph Neural Networks".
Other
235 stars 59 forks source link

Hello, I'm getting the following error while trying to run model test, with part of NTU RGB+D dataset: #23

Open dongle329 opened 4 years ago

dongle329 commented 4 years ago

Model total number of params: 4089320 [ Sat Jun 20 08:05:09 2020 ] Load weights from ./runs/ntu_cs_dgnn_spatial-49-62600.pt. [ Sat Jun 20 08:05:09 2020 ] Model: model.dgnn.Model. [ Sat Jun 20 08:05:09 2020 ] Weights: ./runs/ntu_cs_dgnn_spatial-49-62600.pt. [ Sat Jun 20 08:05:09 2020 ] Eval epoch: 1 0%| | 0/516 [00:05<?, ?it/s] Traceback (most recent call last): File "main.py", line 606, in processor.start() File "main.py", line 567, in start self.eval(epoch=0, save_score=self.arg.save_score, loader_name=['test'], wrong_file=wf, result_file=rf) File "main.py", line 491, in eval output = self.model(joint_data, bone_data) File "/home/min1/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call result = self.forward(*input, kwargs) File "/home/min1/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 155, in forward outputs = self.parallel_apply(replicas, inputs, kwargs) File "/home/min1/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 165, in parallel_apply return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)]) File "/home/min1/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 85, in parallel_apply output.reraise() File "/home/min1/anaconda3/lib/python3.6/site-packages/torch/_utils.py", line 395, in reraise raise self.exc_type(msg) RuntimeError: Caught RuntimeError in replica 0 on device 0. Original Traceback (most recent call last): File "/home/min1/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 60, in _worker output = module(*input, *kwargs) File "/home/min1/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call result = self.forward(input, kwargs) File "/media/min1/cf3d08d5-3d6b-457d-bef5-1b12560aef78/DL/Unofficial-DGNN-PyTorch-master/model/dgnn.py", line 184, in forward fv, fe = self.l2(fv, fe) File "/home/min1/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call result = self.forward(*input, *kwargs) File "/media/min1/cf3d08d5-3d6b-457d-bef5-1b12560aef78/DL/Unofficial-DGNN-PyTorch-master/model/dgnn.py", line 123, in forward fv, fe = self.dgn(fv, fe) File "/home/min1/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call result = self.forward(input, **kwargs) File "/media/min1/cf3d08d5-3d6b-457d-bef5-1b12560aef78/DL/Unofficial-DGNN-PyTorch-master/model/dgnn.py", line 85, in forward fv = fv.view(N, -1, V_node) RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

dongle329 commented 4 years ago

my torch=1.3.1

GedamuA commented 4 years ago

fv = fv.reshape(N, -1, V_node)