In gan.py line 401,
data_ids = np.random.choice(train_size, opts['batch_size'],
replace=False, p=self._data_weights)
Why use replace=False here?

I have implemented a GAN network for predicting future frames of a video. I was wondering how to subject my code to AdaGAN. Any pointers would be really helpful.

tensorflow version: 1.2.1
When I tried to run python adagan_mnist.py, it showed this error:
2017-07-07 19:46:49,618 - Loading MNIST
Traceback (most recent call last):
File "adagan_mnist.py", line 152, in
main()
File "adagan_mnist.py", line 113, in main
data = DataHandler(opts)
File "/home/xiaoyu/adagan/datahandler.py", line 62, in init
self._load_data(opts)
File "/home/xiaoyu/adagan/datahandler.py", line 69, in _load_data
self._load_mnist(opts)
File "/home/xiaoyu/adagan/datahandler.py", line 212, in _load_mnist
tr_X = loaded[16:].reshape((60000, 28, 28, 1)).astype(np.float)
ValueError: cannot reshape array of size 9912406 into shape (60000,28,28,1)
The dataset is downloaded from the MNIST website. So does anyone have any idea about what's wrong?

On running adagan_mnist.py, I am getting the following error:

tr_X = loaded[16:].reshape((60000, 28, 28, 1)).astype(np.float)
ValueError: cannot reshape array of size 9912406 into shape (60000,28,28,1)

On printing the size of "loaded", it shows (9912422,)
And loaded[16:] is (9912406,)

So I changed loaded[16:].reshape ... in line 411 to loaded.reshape ...

Still getting the same error with new array size:

tr_X = loaded.reshape((60000, 28, 28, 1)).astype(np.float)
ValueError: cannot reshape array of size 9912422 into shape (60000,28,28,1)

Thank you very much for your fantastic code. But I wanna know what's the meaning of POT in your code?

Thanks for your answer!