Should x_hat also be used for prediction period?

[carsonDB]

It may not be a problem, but I am just curious about why x_hat (involving true data) is also used for prediction period. Because I think, after training, the model should produce data independently, not by means of true data.

Details as follows: Read x as well as x_hat x = filter_img(x, Fx, Fy, gamma, read_n) # batch x (read_n*read_n) x_hat = filter_img(x_hat, Fx, Fy, gamma, read_n) After the training: canvases = sess.run(cs, feed_dict) # generate some examples canvases = np.array(canvases) # T x batch x img_size

It seems that, x_hat is also fed into the model. But x_hat contains the true data.

Thanks!