Closed yghlc closed 7 years ago
This code was tested on a Nvidia Titan X GPU, where it was occupying about 11.9 GB of memory. Therefore, it would not run on a 8 GB GPU. You can use this .pth file which I trained myself on the train set of VOC2012. If you disable the scale augmentation in train.py then I think you should be able to accommodate it in a 8 GB GPU. You will have to modify some parts of train.py to remove the scale augmentation.
Dear all, I tried to train the model with VOC2012, but had error: out of memory. Following is the output message,
The memory of my GPU is 8 GB, and the batchsize used in the code is 1. Any idea to this error? Thanks for your help.