bluestyle97 / stgan-pytorch Goto Github PK

Could your please help me how to fix the error "Please wait while finalizing the operation.. Thank you
" when running the main.py

Thank you very much for the code you provided.But there is a question for me.In the stgan.py,I found the 'shortcut_layers' which I couldn't match to the paper,could you please tell me the meaning of it?
Thank you very much.

hello, thanks for your sharing. Could you please tell me how much time this project cost ? several days ? and how many GPUS you used？

print(' The experiment model is {} '.format(config.model_name))
AttributeError: 'EasyDict' object has no attribute 'model_name'

thank you very much for this great work.
when I run your code,i find that the results on "add eyeglass" are the same as sources image.
is there mode collapse in "add eyeglass" attribute.
by the way,why does the tensorflow code have a more excellent results than pytorch code?

Sorry,I come again.There is a question for me.
When I run the models/stgan.py
the screen displays---TypeError: can't multiply sequence by non-int of type 'tuple'.
Could you please tell me the reason of this error?
Thank you very much.

Hi, can you please help me to run the code completely. whenever i try to run the train.py module, it produce following information and then stop. currently i am trying to run the code in Google colab.

The experiment name is stgan
The experiment mode is train

directory created successfully
[INFO]: Hi, This is root.
[INFO]: After the configurations are successfully processed and dirs are created.
[INFO]: The pipeline of the project will begin now.
[INFO]: Creating STGAN architecture...
[INFO]: Operation will be on GPU-CUDA
[INFO]: __Python VERSION: 3.8.10 (default, Nov 14 2022, 12:59:47)
[GCC 9.4.0]
[INFO]: __PyTorch VERSION: 1.13.1+cu116
[INFO]: __CUDA VERSION
cat: /usr/local/cuda/version.txt: No such file or directory
[INFO]: __CUDNN VERSION: 8302
[INFO]: __Number CUDA Devices: 1
[INFO]: __Devices
index, name, driver_version, memory.total [MiB], memory.used [MiB], memory.free [MiB]
0, Tesla T4, 510.47.03, 15360 MiB, 3 MiB, 15106 MiB
[INFO]: __Active CUDA Device: GPU 0
[INFO]: __Available devices 1
[INFO]: __Current cuda device 0
Please wait while finalizing the operation.. Thank you

Hi, bluestyle97!
Thanks for your nice pytorch reimplementation! It more faster than official version. But, i found some difference: 1. conv without bias . 2. target label has a randmom coefficient multiplied. Could you explain that? I am confusing about why you did this. thank you very much!

i am a pytorch rookie, can you launch the tset file here?
thank you very much