Xiao Feng Zhang

i want to change mask,a problem occured

5

it's my code : ```python def mask_width(img): image = img.copy() height = image.shape[0] width = image.shape[1] new_width = int(width * MASK_PERCENTAGE) mask = np.ones([height, new_width, 3]) missing_x = img[:, :new_width]...

train epoch

1

if i set epoch=200,will the result become worse? must i set epoch=500 and the train result could be the best?

Train problem

1

i run main(),and a problem occured PermissionError: [Errno 13] Permission denied: '/img_0_2019-12-02-12-53-11.jpg'

main() problem.

1

Found 0 images belonging to 0 classes. Traceback (most recent call last): File "/home//PConv-Keras-master/main.py", line 180, in test_data = next(test_generator) File "/home//PConv-Keras-master/main.py", line 122, in flow_from_directory for _ in range(ori.shape[0])],...

非常感谢老哥的开源代码，训练完以后我运行translate.py 出现了编码问题，目前用的是ubuntu-18，txt文件我看到都是utf-8编码的，应该没问题阿？ UnicodeDecodeError: 'utf-8' codec can't decode byte 0xbb in position 33: invalid start byte

test_contextual_attention()

1

Hello, thanks for your contributions, but how should i test attention map? What command should i set it ?

pretrained model

5

could you share other pretrained model like place2 or cityspace. if you are convenient,please share it. or can you send to my address [email protected]?? thank you very much!!

train problem

5

for example,if i use celebahq,i should follow the cmd：python train.py --dataset celebahq --data_file /data/yiwang/download/celeba_hd_256/train.txt --gpu_ids 0 --max_iters 80000 --g_cnum 64 --pretrain_network 1 --batch_size 8 --model srn --feat_expansion_op subpixel --random_mask 1...

Hi，Honlan，i am appreciate it for your work,and i am trying to De-make up,How should i do it ?