the crop_to_shape(data, shape) function not work right

[LilianYe]

when (data.shape[1] - shape[1]) % 2 == 1, the return size is shape[1]+1 but not shape[1].

[jakeret]

Yes this has been an issue for a while. Could you send me a Pull Request for that?

[lixiangamy]

feed_dict={self.net.x: batch_x, self.net.y: util.crop_to_shape(batch_y, pred_shape), self.net.keep_prob: dropout})

why batch_y.shape!=pred_shape?

[jakeret]

Due to the network architecture the output prediction are always smaller than the input labels