Closed Abhijithchintu closed 3 years ago
It is in base_dataset.py file , maybe p1_path is not correct
You need to split images into train/test folder by changing the related path in data/generate_fashion_datasets.py anda running it. Please note that using low-resolution images. And the data preparation is followed Pose Transfer and GFLA, it will be apperatiated if you can refer to them firstly.
Can you share the .ipynb file where you run this code
Abhijith
On Wed, 14 Apr, 2021, 18:56 jinszhang, @.***> wrote:
You need to split images into train/test folder by changing the related path in data/generate_fashion_datasets.py anda running it. Please note that using low-resolution images. And the data preparation is followed Pose Transfer https://github.com/tengteng95/Pose-Transfer and GFLA https://github.com/RenYurui/Global-Flow-Local-Attention/blob/master/PERSON_IMAGE_GENERATION.md, it will be apperatiated if you can refer to them firstly.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/Zhangjinso/PISE/issues/13#issuecomment-819516917, or unsubscribe https://github.com/notifications/unsubscribe-auth/ARG37O7EE4B2JIGH35EJSLLTIWJZHANCNFSM425IGANA .
I didn't use colab to do.the project. Sorry about that. You can refer to GFLA, it has a colab version.
---Original--- From: @.> Date: Wed, Apr 14, 2021 21:54 PM To: @.>; Cc: @.>;"State @.>; Subject: Re: [Zhangjinso/PISE] Error while training (#13)
Can you share the .ipynb file where you run this code
Abhijith
On Wed, 14 Apr, 2021, 18:56 jinszhang, @.***> wrote:
> You need to split images into train/test folder by changing the related > path in data/generate_fashion_datasets.py anda running it. Please note that > using low-resolution images. And the data preparation is followed Pose > Transfer <https://github.com/tengteng95/Pose-Transfer> and GFLA > <https://github.com/RenYurui/Global-Flow-Local-Attention/blob/master/PERSON_IMAGE_GENERATION.md>, > it will be apperatiated if you can refer to them firstly. > > — > You are receiving this because you authored the thread. > Reply to this email directly, view it on GitHub > <https://github.com/Zhangjinso/PISE/issues/13#issuecomment-819516917>, or > unsubscribe > <https://github.com/notifications/unsubscribe-auth/ARG37O7EE4B2JIGH35EJSLLTIWJZHANCNFSM425IGANA> > . >
— You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub, or unsubscribe.
I just check the code about data/generate_fashion_dataset.py, you just need to replace 'img_highres' to 'img' and change the last line to you folder where you put the images. If it is not successful, you can read the coda about generate_fashion_dataset.py. It is easy to get.
Still getting same error , there must be something wrong in the path of calling , ./dataset/fashion_data/train/fashionWOMENJackets_Coatsid00006582033back.jpg In the above line till train it is ok , but after that there is fashion , WOMEN , jackets and not differntiated by and also id_00006582 must be there not id00006582
while training we are getting this error eventhough we have downloaded datasets and put it in fashiondata directory and in train. FileNotFoundError: [Errno 2] No such file or directory: './dataset/fashion_data/train/fashionWOMENJackets_Coatsid0000658203_3back.jpg' Here Women and jackets are directories but it is showing as single name , and also 03 should be in folder of id_00006582