The time of loading for the training data about mbrs HOT 4 CLOSED

Besides,What is the ratio between training datasets and validation datasets?

from mbrs.

Hello, thanks for your issue. It's just because I forget to change the loading function in the code.

In fact I load the whole dataset into the memory before training. It takes long time to load them at once, but will speed up the later training, just like a future step for pin_memory (you can find I store the loaded dataset in train_dataloader in train.py).

But it seems not the normal usage of torch.utils.data.dataset, so I will change it back to use getitem function, before next Monday.

For the training time, it takes about 12 hours to train the model MBRS_256_256 which embeds 256bits into a 256*256 RGB image, with 4 2080Ti GPUs. And it will be much quicker to train for a 128*128 image.

from mbrs.

In my implementation, I used 5000 images for validation because it didn't take much time. You can change it as you like.

from mbrs.

Code updated. Closed.

from mbrs.