Run the truning in my own data

[ghost]

Hello,

Thanks for the great work.

The training/evaluation code works perfectly with KolektorSDD (with dilate=5 for mask) dataset. But, when I run the training on my dataset, tensorflow ends up in an infinite loop in the line 395 (see here).

To generate the TFRecords, I used your code: input_data/input_data_build_image_data_with_mask.py..

Please find below the link to my generated data: train-00000-of-00001

I'd be very grateful if you could help me to solve this problem.

Thank you in advance

[huiguobao]

@ghost , I have the same problem, have you solved it and how to solve it? Thanks