Traceback (most recent call last):
File "train.py", line 251, in
main()
File "train.py", line 228, in main
loss.backward()
File "/home/tongxuedong/anaconda3/envs/pytorch-gpu/lib/python3.6/site-packages/torch/tensor.py", line 118, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/tongxuedong/anaconda3/envs/pytorch-gpu/lib/python3.6/site-packages/torch/autograd/init.py", line 93, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: CUDA out of memory. Tried to allocate 86.00 MiB (GPU 3; 11.75 GiB total capacity; 10.05 GiB already allocated; 85.81 MiB free; 588.65 MiB cached)
Hello, when I run this script on 4 x TiTAN V , it occur issues above. How cao I do? Please help me.
Traceback (most recent call last): File "train.py", line 251, in
main()
File "train.py", line 228, in main
loss.backward()
File "/home/tongxuedong/anaconda3/envs/pytorch-gpu/lib/python3.6/site-packages/torch/tensor.py", line 118, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/tongxuedong/anaconda3/envs/pytorch-gpu/lib/python3.6/site-packages/torch/autograd/init.py", line 93, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: CUDA out of memory. Tried to allocate 86.00 MiB (GPU 3; 11.75 GiB total capacity; 10.05 GiB already allocated; 85.81 MiB free; 588.65 MiB cached)
Hello, when I run this script on 4 x TiTAN V , it occur issues above. How cao I do? Please help me.