Dear author, I tried to train your model on one 4090 gpu. I reduce the batch_size to 1 to fit the gpu memory, but it gives me this error during forward: ``` RuntimeError: no valid convolution algorithms available in CuDNN ``` Do you know how to solve it?
Dear author,
I tried to train your model on one 4090 gpu. I reduce the batch_size to 1 to fit the gpu memory, but it gives me this error during forward:
Do you know how to solve it?