DeepFillv2_Pytorch

DeepFillv2_Pytorch copied to clipboard

fix small bug in tester

1

Fix small bugs that add namespace(opt) for 'results_path'.

xtliu97

The hyperparameters of loss functions are not the same as the official tensorflow implementation.

2

Hi there, I have noticed that you have set the ratio between `l1 loss`, `perceptual loss` and `adversarial loss` as `100: 10: 1`, which is not the same as the...

AlonzoLeeeooo

tengshaofeng

Thank you for sharing the code. I believe the line (# 135 in trainer.py) when you are creating the mask is incorrect, because you use img.shape[0] (which is the number...

Onypony

Trouble with quality of results using pretrained model

11

Used the pretrained model against a test image of my own, and the results are not good at all. Curious if there are any thoughts on what might be causing...

dwallener

use pretrained model to show the official results,but failed.

1

is this some wrong with me? the masked region is overlaped with some red strange patch. python = 3.6. torch = 1.5.0.

wmnj

Hello thanks for sharing your work. I am trying training the model with CelebA datasets but the loss function when training is too large. Do you think this loss function...

huynth1801

could you provide a script to export an onnx model?

1

could you provide a script to export an onnx model?

ajq2020

Hi. Thanks for your re-implementation. I got several questions when I was training other settings according to the paper. The author of DeepFillv2 said that this model can be trained...

AlonzoLeeeooo

几个epoch之后就爆显存，把batch_size设置为1或2时不会出现这个问题，但是在test时直接把输入图像输出了，mask部分变成了黑色

Dominic-ZZ