f23f2ff2c96537274beb99aca8417f054f817501,examples/neural_style_transfer.py,,,#,282

Before Change

// so as to minimize the neural style loss
x = np.random.uniform(0, 255, (1, 3, img_width, img_height))
x[0, 0, :, :] -= 103.939
x[0, 1, :, :] -= 116.779
x[0, 2, :, :] -= 123.68
for i in range(10):
    print("Start of iteration", i)

After Change

// run scipy-based optimization (L-BFGS) over the pixels of the generated image
// so as to minimize the neural style loss
if K.image_dim_ordering() == "th":
    x = np.random.uniform(0, 255, (1, 3, img_width, img_height)) - 128.
else:
    x = np.random.uniform(0, 255, (1, img_width, img_height, 3)) - 128.

for i in range(10):
    print("Start of iteration", i)
    start_time = time.time()
    x, min_val, info = fmin_l_bfgs_b(evaluator.loss, x.flatten(),

Instances