DragonDreamer

```python for datatype in ['train', 'val', 'test']: os.system('mkdir ' + datatype) data=pd.read_csv(datatype + '.csv') label_set = set(data['label']) for label in label_set: cur_dir = datatype + '/' + label + '/'...

Firstly, sub-type extends `Object` are removed in reflections. So I create a new class named `MySuperClass` as the super class, then you can get access to the anonymous class with...

@ronmamo I update a case about this in #370 . Please have a review and test.

> I haven't updated this code for a while. I would not be surprised if one of the latest updates of tensorflow broke my code. Sir, i use the same...

> Hi, > I simply ran train_one_shot_learning_matching_network.py following guideline in the Readme file, then I met following error. Does anyone meet the same problem? > > Traceback (most recent call...