Expected a Tensor of type torch.FloatTensor but found a type torch.cuda.FloatTensor for sequence element 5 in sequence argument at position #1 ‘tensors’
tensor([13, 0, 63, -1], device=‘cuda:0’)
tensor([17, 0, 69, -1], device=‘cuda:0’)
tensor([20, 0, 74, -1], device=‘cuda:0’)
tensor([25, 0, 78, -1], device=‘cuda:0’)
Expected a Tensor of type torch.cuda.FloatTensor but found a type torch.FloatTensor for sequence element 1 in sequence argument at position #1 ‘tensors’
CUDA error: out of memory
THCudaCheck FAIL file=/pytorch/aten/src/THC/generic/THCTensorMath.cu line=35 error=2 : out of memory
cuda runtime error (2) : out of memory at /pytorch/aten/src/THC/generic/THCTensorMath.cu:35
CUDA error: out of memory (allocate at /pytorch/aten/src/THC/THCCachingAllocator.cpp:510)
frame #0: THCStorage_resize + 0x123 (0x7f695dd4a123 in /home/coea/.local/lib/python3.5/site-packages/torch/lib/libcaffe2_gpu.so)
frame #1: THCTensor_resizeNd + 0x293 (0x7f695dd55633 in /home/coea/.local/lib/python3.5/site-packages/torch/lib/libcaffe2_gpu.so)
frame #2: THCudaTensor_catArray + 0x295 (0x7f695de03a35 in /home/coea/.local/lib/python3.5/site-packages/torch/lib/libcaffe2_gpu.so)
Training a model with CNN+LSTM+CTC loss getting this error… Please help me out. Thanks in advance.