search

taoxugit / AttnGAN

MIT License
1.33k stars 415 forks source link

Validation generates 2928 instead of 2933 reported in paper and dataset.__len__ #38

Open shengyuzhang opened 5 years ago

shengyuzhang commented 5 years ago

Hi, I run the following code to make validation on trained Attn Generator: python main.py --cfg cfg/eval_bird.yml --gpu 1 but resulted in getting 2928 images instead of 2933 reported in paper "Statistics of datasets" and using dataset.len (2933 as well)

I think Pytorch Dataloader initialization param "drop_last" is the key. However, when I set it to False, the code raised an error saying: RuntimeError: Expected hidden[0] size (2, 5, 128), got (2, 16, 128) indicating that the last batch failed and batch_size instead of input.size[0] is used to struct the model, which results in that the number of generated images varies with different batch_size setup.

How can I solve this issue?

shengyuzhang commented 5 years ago

2933 = 7 * 419

I set the batch_size to 7 and get 2933 images. So why the batch_size in the public eval_bird.yml is set to 16? I mean, is there any setup that can allow me to use an arbitrary batch_size?