Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

where is “~/.keras/datasets/VOC2012/combined_imageset_train.txt” #58

Open
PellyKoo opened this issue Dec 26, 2017 · 11 comments
Open

Comments

@PellyKoo
Copy link

Thank you for your code.
I've already download voc2012 dataset. But I didn't find this file“combined_imageset_train.txt”,Similarly, I didn't find “combined_imageset_val.txt”,If you are free, please tell me

@ahundt
Copy link
Collaborator

ahundt commented Dec 26, 2017

the scripts should generate those files if you follow the readme instructions

@duan147
Copy link

duan147 commented Jan 31, 2018

I don't know why, I didn't generate this file. Can you tell you what you have done to generate it?thanks

@PellyKoo
Copy link
Author

@duan147 You should download “tf_image_segmentation”,and run “python data_pascal_voc.py” in a terminal window.

@PellyKoo
Copy link
Author

@duan147 PS:Follow “readme.md”instructions

@duan147
Copy link

duan147 commented Jan 31, 2018

@PellyKoo Thank you. I'll try it.

@duan147
Copy link

duan147 commented Jan 31, 2018

@PellyKoo I'd like to ask, are you through this code? If you can, can you add a contact number? Thank you.

@PellyKoo
Copy link
Author

@duan147 OK.my E-mail address:pellykoo@foxmail.com

@simonsayshi
Copy link

@ahundt hi, I've run the 'python data_pascal_voc.py pascal_voc_setup' they generate two label folder and a folder named 'trainval' but there is no file named combined_images_train.txt, why is that?

@jiyeonBaek
Copy link

Hello, I have same problem. I got all dataset except "combined_imageset_train.txt" , "combined_imageset_val_txt" . If it is okay, can I get those file through Email? Mine is qor3429@gmail.com . Thanks.

@F951
Copy link

F951 commented Jun 21, 2018

Hi, in the main part of "train.py", in the "if dataset == 'VOC2012_BERKELEY':" section, set:

train_file_path=os.path.expanduser('~.keras/datasets/VOC2012/VOCdevkit/VOC2012/ImageSets/Segmentation/train.txt')   
val_file_path=os.path.expanduser('~.keras/datasets/VOC2012/VOCdevkit/VOC2012/ImageSets/Segmentation/val.txt')
data_dir = os.path.expanduser('~.keras/datasets/VOC2012/VOCdevkit/VOC2012/JPEGImages')
label_dir= os.path.expanduser('~.keras/datasets/VOC2012/VOCdevkit/VOC2012/SegmentationClass')

Regards

@pkuyilong
Copy link

Maybe there is something wrong with your network, connection failed or read timeout cause this problem. I met this problem when i first run, next running result is correct.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

7 participants