Hi,

I can't find the datasets you are training on in your YAML files. Could you please tell me where to download them ?

Regards

Dear Ruilong Li,

Thank you for implementing this. It is excellent work to reproduce the training code with python.

However, I found two issues after I trained the model several epochs. I trained with my own data with initial model completionnet_places2.t7. On the first of the epochs, it would do an OK job, however, there is a gray frame covered.

This image is generated from my own data set. And you can see a grey box is covered on top of that.

After several epochs, the completion part is totally black. Could you explain why? Is it because overfiting?

Here is an artifact generated after 10 epochs. You can see a black box in the image. This is generated from the Places dataset.

Again, thank you for your work and I really appreciate your hard work. Many thanks to your reply.

Best,
Miao Jiang

Hi Ruilong Li,

I found another bug after modifying epochs for G and D.

Here is the report.
Traceback (most recent call last):
File "train.py", line 592, in
main()
File "train.py", line 531, in main
train(dataLoader, model_G, model_D, epoch)
File "train.py", line 450, in train
losses_G.update(loss_G.data[0], input3ch.size(0))
AttributeError: 'AverageMeter' object has no attribute 'data'

Does the data here mean val?

Best,
Miao