Error occurred when converting Pytorch model to GPU model

because there is no PyTorch tag at present, so TensorFlow is used. Would you like to add this tag to those with high reputation? Thanks tags ()

recently, I"m going to use the VGG model to train the data, and then I want to use GPU, but I always report an error when converting the VGG model to VGG.cuda (). At first, I thought it was a problem with the dataset, but then I converted VGG to .cuda () without doing anything, but I still reported an error. The code and error report are as follows:


hint: is there not enough video memory in out of memory,? I tried it, pytorch 0.3.1 + torchvision 0.2.0 to load VGG16 requires more than 700 MB memory:

clipboard.png

you can try a smaller model or see if there is a problem with cuda.

Menu