Facelet_Bank

Facelet_Bank copied to clipboard

你好，这个程序可以在Windows系统上跑吗，我试着运行了，可是报了一些错误。

137506942

KeyError: 'module name can\'t contain "."'

3

Traceback (most recent call last): File "test_facelet_net.py", line 110, in Framework.run() File "D:\xinghu\Facelet_Bank\util\framework.py", line 32, in run self.func_dict[args.command]() File "test_facelet_net.py", line 81, in test_video decoder = vgg_decoder() File "D:\xinghu\Facelet_Bank\network\decoder.py", line...

MollyHoo

The training results cannot be reproduced. Could you provide the epoch, batch_size, and learning_rate parameters used to generate the pre-trained model?

crystalphi

@yingcong Thanks for the code! Have you tried Facelet Bank for other attributes such as bangs and eyeglasses?

LynnHo

How to show the heatmap using trianed models?

1

Has anyone used trained model to get the heat map? I want to get heat map images by using trained model inside the facelet_bank.

MdAshrafulAlam

Decoder training

3

Hi. I'm trying to reproduce your results on smaller images, but it seems that decoder doesn't work correctly with such sizes Can you expand on how you trained `vgg_decoder`?

kilotaras

slow test speed

4

Is it normal to test slowly? I have used GPUs，A picture feels like it takes five minutes。

shenshenzhanzhan

``` $ python test_facelet_net.py test_image --input_path examples/input.png --effect younger --strength 5 -cpu RuntimeError: $ Torch: not enough memory: you tried to allocate 2GB. Buy new RAM! at /pytorch/torch/lib/TH/THGeneral.c:253 ``` Tried...

AidasK

input.size[1] == 3 but got 4 instead

5

Hi,@yingcong , it has 4 channels when I input a color picture with your code like this:  do you know the reason? thank you!

Amanda-Barbara