OOM even when using batch size 1, total image count 1, tag count 4 and input size 1x1 about deepdanbooru HOT 2 CLOSED

DeepDanbooru uses CNN network and GAP for last output. So input size and output size does not much affect total memory usage. It requires more than 500MB for the model itself. And the same size of memory is needed for training with minibatch size 1 at least. I think 1.3GB is too small to train DeepDanbooru model.

You can try decreasing model size by modifying source code:

from deepdanbooru.

Thanks for the reply.

Modifying network structure is not a preferred choice for me bacause I want to retrain existing network (my dataset is too small for training from scratch).

I will try to use Google Colab, presumably they allow to use 12 GB per user.

from deepdanbooru.