error running test.py

[ghost]

while running the test.py file after loading the network and datasets this error pops up. system specifications: Ubuntu 16 pytorch: 1.1.0 cuda: 10

Output of: "python test.py --name edge2face_512 --dataroot datasets/face/ --dataset_mode face --input_nc 15 --loadSize 512 --use_single_G" ------------ Options ------------- ... ... ... -------------- End ---------------- CustomDatasetDataLoader dataset [FaceDataset] was created ---------- Networks initialized -------------

Doing 28 frames THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=383 error=11 : invalid argument Traceback (most recent call last): File "test.py", line 42, in generated = model.inference(A, B, inst) File "/vid2vid1/vid2vid/models/vid2vid_model_G.py", line 200, in inference self.fake_B_prev = self.generate_first_frame(real_A, real_B, pool_map)
File "/vid2vid1/vid2vid/models/vid2vid_model_G.py", line 239, in generate_first_frame feat_map = self.get_face_features(real_B[:,i], pool_map[:,i]) if self.opt.dataset_mode == 'face' else None File "/vid2vid1/vid2vid/models/vid2vid_model_G.py", line 294, in get_face_features feat_map = self.netE.forward(real_image, inst)
File "/vid2vid1/vid2vid/models/networks.py", line 585, in forward outputs = self.model(input) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(*input, *kwargs) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/container.py", line 92, in forward input = module(input) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(input, **kwargs) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/conv.py", line 338, in forward self.padding, self.dilation, self.groups) RuntimeError: cuda runtime error (11) : invalid argument at /pytorch/aten/src/THC/THCGeneral.cpp:383

Does anyone know how to fix this or even why does it happen? I really appreciate any help.