generative_inpainting
generative_inpainting copied to clipboard
JiahuiYu
DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
Really nice work and great idea for the DeepFillv2!! Any plan and expected date to release the DeepFillv2 code?
Hi, Jiahui! After an one-week training on a GTX 1080TI, I found some interesting results from my own dataset. There are 2 kinds of images in my dataset. One is...
I have found some issues about this in [#73](https://github.com/JiahuiYu/generative_inpainting/issues/73) and [#22](https://github.com/JiahuiYu/generative_inpainting/issues/22) and according to the [link](https://distill.pub/2016/deconv-checkerboard/) provided by @JiahuiYu , I did some experiments and tried to explain it here....
I would like to change some layers of a trained model for transition learning, but I don't know how to change only a part of the model. Can someone please...
when meet yi = yi*mm in contextual_attention,the error occurs. tensorflow.python.framework.errors_impl.InvalidArgumentError: required broadcastable shapes [Op:Mul] can anyone help me?
Hi I am trying to train the model on own dataset but colab is not supporting tensorflow applied in this model. Urgent help is appreciated. Regards
@JiahuiYu Salutations, Examining the original publication, it is indicated that the inputs (I) to a gated convolution are convolved with different weights (one set for features: W_f and another for...
Hello, I encountered an AssertionError while training a model, indicating that the loss_value is NaN. I'd like to get some assistance or insights into why this might be happening and...
what's difference between https://github.com/zuruoke/watermark-removal and this repo?
I write something easy to modify. ``` from random import shuffle import os train_filename = 'G:/image_inpainting/train_shuffled.flist' validation_filename = 'G:/image_inpainting/validation_shuffled.flist' training_file_names = [] validation_file_names = [] training_path = 'G:/image_inpainting/training' validation_path =...
