RuntimeError: CUDA error: out of memory

liyunsheng13 / BDL

MIT License

222 stars 30 forks source link

RuntimeError: CUDA error: out of memory #20

Open Ha0Tang opened 5 years ago

Ha0Tang commented 5 years ago

Hi, when I am trying to test the pre-trained VGG models, I got the "out of memory" error. Can you help me to fix it? Thanks.

liyunsheng13 commented 5 years ago

I'm sorry. I'm not able to solve out of memory problem. Maybe your GPU doesn't have enough memory. But I think 12Gb is enough.

Ha0Tang commented 5 years ago

I tested on a Titan X GPU with 12Gb memory.

liyunsheng13 commented 5 years ago

That's very weird to me. Up till now, no one has even reported the out of memory problem when testing the model. 12Gb is very enough. Do you resize the image to 512*1024 with batch size = 1

Ha0Tang commented 5 years ago

Is there any hyper-parameter need to set for image resolution?

liyunsheng13 commented 4 years ago

The size of the input images have been set in the file of BDL/data/init.py. At least, you should run the evaluation.py code and check the image size you load.