RuntimeError: CUDA error: out of memory

[adityaguptai]

RuntimeError: CUDA error: out of memory Running out of memory have 2gb graphics card 940mx with cuda 9.2 is it not sufficient to train the model. I tried decreasing the batch size to even 1 but then too its not working. Please help.

[atulkum]

2GB is too low. you can do 2 things:

1. use pre-trained embedding, extract embedding vector on cpu and don't load embedding into gpu.
2. use less number of encoding steps (try with 100) but expect degrade in results. https://github.com/atulkum/pointer_summarizer/blob/master/data_util/config.py#L16