Loading seed from an image.

README.rst

@@ -110,7 +110,7 @@ Installation & Setup
 
 This project requires Python 3.4+ and you'll also need ``numpy`` and ``scipy`` (numerical computing libraries) as well as ``python3-dev`` installed system-wide.  If you want more detailed instructions, follow these:
 
-0. Use Pre-Installed `Docker Container <https://github.com/alexjc/neural-doodle/issues/61>`_ or `Amazon Image <https://github.com/alexjc/neural-doodle/issues/54>`_ (beginner).
+0. Use Prepared `Docker Container <https://github.com/alexjc/neural-doodle/issues/61>`_ or `Amazon Image <https://github.com/alexjc/neural-doodle/issues/54>`_ **(beginner)**
 1. `Linux Installation of Lasagne <https://github.com/Lasagne/Lasagne/wiki/From-Zero-to-Lasagne-on-Ubuntu-14.04>`_ **(recommended)**
 2. `Mac OSX Installation of Lasagne <http://deeplearning.net/software/theano/install.html#mac-os>`_ **(intermediate)**
 3. `Windows Installation of Lasagne <https://github.com/Lasagne/Lasagne/wiki/From-Zero-to-Lasagne-on-Windows-7-%2864-bit%29>`_ **(expert)**

doodle.py

@@ -518,6 +518,10 @@ def run(self):
             if args.seed == 'previous':
                 Xn = scipy.misc.imresize(Xn[0], shape, interp='bicubic')
                 Xn = Xn.transpose((2, 0, 1))[np.newaxis]
+            if os.path.exists(args.seed):
+                seed_image = scipy.ndimage.imread(args.seed, mode='RGB')
+                self.seed_image = self.model.prepare_image(seed_image)
+                Xn = self.seed_image[0] + self.model.pixel_mean
 
             # Optimization algorithm needs min and max bounds to prevent divergence.
             data_bounds = np.zeros((np.product(Xn.shape), 2), dtype=np.float64)