You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
在Colab上报错:
Log file stylegan_bedroom_manipulation/log.txt has already existed!
Would you like to overwrite it (Y/N): Y
[2021-04-13 09:53:49,930][WARNING] Overwriting log file stylegan_bedroom_manipulation/log.txt!
[2021-04-13 09:53:49,930][INFO] Initializing generator.
[2021-04-13 09:53:49,937][INFO] Build generator for model stylegan_bedroom.
[2021-04-13 09:53:50,190][INFO] Loading pytorch weights from models/pretrain/pytorch/stylegan_bedroom256_generator.pth.
[2021-04-13 09:53:50,534][INFO] Successfully loaded!
[2021-04-13 09:53:52,528][INFO] Current lod is 0.0.
[2021-04-13 09:53:52,528][INFO] Preparing latent codes.
[2021-04-13 09:53:52,528][INFO] Sample latent codes randomly.
Traceback (most recent call last):
File "manipulate.py", line 280, in
main()
File "manipulate.py", line 171, in main
boundaries = parse_boundary_list(args.boundary_list_path)
File "/content/higan/utils/editor.py", line 383, in parse_boundary_list
for line in f:
File "/usr/lib/python3.7/codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x93 in position 0: invalid start byte
问题出现在/utils/editor.py的383行:
for line in f:
似乎是382行使用open函数无法正确打开boundary list的.npy文件:
with open(boundary_list_path, 'r') as f:
沈博您好,我通过以下设置运行 manipulate.py:
LAYERS=6-11
python manipulate.py $MODEL_NAME $BOUNDARY_LIST
--num=10
--layerwise_manipulation
--manipulate_layers=$LAYERS
--generate_html
在Colab上报错:
Log file
stylegan_bedroom_manipulation/log.txt
has already existed!Would you like to overwrite it (Y/N): Y
[2021-04-13 09:53:49,930][WARNING] Overwriting log file
stylegan_bedroom_manipulation/log.txt
![2021-04-13 09:53:49,930][INFO] Initializing generator.
[2021-04-13 09:53:49,937][INFO] Build generator for model
stylegan_bedroom
.[2021-04-13 09:53:50,190][INFO] Loading pytorch weights from
models/pretrain/pytorch/stylegan_bedroom256_generator.pth
.[2021-04-13 09:53:50,534][INFO] Successfully loaded!
[2021-04-13 09:53:52,528][INFO] Current
lod
is 0.0.[2021-04-13 09:53:52,528][INFO] Preparing latent codes.
[2021-04-13 09:53:52,528][INFO] Sample latent codes randomly.
Traceback (most recent call last):
File "manipulate.py", line 280, in
main()
File "manipulate.py", line 171, in main
boundaries = parse_boundary_list(args.boundary_list_path)
File "/content/higan/utils/editor.py", line 383, in parse_boundary_list
for line in f:
File "/usr/lib/python3.7/codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x93 in position 0: invalid start byte
问题出现在/utils/editor.py的383行:
for line in f:
似乎是382行使用open函数无法正确打开boundary list的.npy文件:
with open(boundary_list_path, 'r') as f:
我已在colab和本地都进行了尝试,均在此处报错。
我也尝试修改open函数的encoding,也没有解决。
能否请您在百忙之中看一下我的问题,十分感谢!
祝好!
The text was updated successfully, but these errors were encountered: