XYAskWhy

> Hi, thanks for your interests to nn-Meter! We have the plan to release the code of data generation. Due to other features with higher priority, the dataset generation code...

> That's right. To test the model level prediction accuracy, you should generate some sample based on different network architecture. We plan to release the code of data generation in...

Thanks @jakubczakon , I had done `prepare_metadata` and `prepare_masks` then, and the problem is we must prepare masks first.

@dslwz2008 If you prepare metadata first, you need to redo it after you prepare mask. Then the newly generated csv file will include a extra column like `'file_path_mask_eroded_0_dilated_0'`.

Got the local training running using the older `master` version, but still struggling with evaluating/predicting. The updated `master` version should be OK as well. @dslwz2008

@jakubczakon Many thanks, but training configuration might not be practical, since most mainstream GPUs now have about 10G memory while the 20 images batch only use 2G. As a result,...