Imran us Salam

``` Preparing training ... Building Training... Traceback (most recent call last): File "preprocess.py", line 71, in main() File "preprocess.py", line 49, in main train = table.IO.TableDataset(opt.train_anno, fields, opt, True) File...

Test on a single Already Perturbed Image

2

Is there any way to use the already trained celeba model (trained with train.py) and infer for a single perturbed image and see if the model regenerates the original?

Added python 3 support

Would it be possible if you could upload the pre-trained model or make some API to get results for the aerial images? I have a bunch of low quality Aerial...