Is the test.ipynb up-to-date ?

nipponjo / deepfillv2-pytorch

A PyTorch reimplementation of the paper Free-Form Image Inpainting with Gated Convolution (DeepFill v2) (https://arxiv.org/abs/1806.03589)

145 stars 34 forks source link

Is the test.ipynb up-to-date ? #24

Closed lchauvin closed 1 year ago

lchauvin commented 1 year ago

Hello,

In your test.ipynb, you create a Generator with cnum_in=5, but you pass as input an image with 3 channels only.

Is it up-to-date with the current train.py code ? Should you also concatenate the ones and ones*mask to the image channel to pass as input, like in the training ?

Thanks.