def get_squeezenet_model(layers):
base_model = SqueezeNet(content_layers)
all_n = []
all_n = get_ckpt_weights('../squeezenet_weights/squeezenet.ckpt')
all_weights = []
for w in base_model.model.weights:
all_weights.append(all_n[weight_to_weight[w.name]])
base_model.set_weights(all_weights)
base_model.trainable = False
dream_model = base_model
return dream_model
return total_variation_weight * tf.image.total_variation(img)
if __name__ == '__main__':
m = SqueezeNet()
all_n = []
all_n = get_ckpt_weights('../squeezenet_weights/squeezenet.ckpt')
all_weights = []
for w in m.model.weights:
all_weights.append(all_n[weight_to_weight[w.name]])
m.set_weights(all_weights)
m.trainable = False
sw = 0.012
params1 = {
'content_image': 'styles/blackpool.jpg',
#'style_image' : 'styles/composition_vii.jpg',
#'style_image' : 'styles/muse.jpg',
#'style_image': 'styles/starry_night.jpg',
#'style_image': 'styles/impr_sunset.jpg',
#'style_image': 'styles/the_scream.jpg',
#'style_image': 'styles/mona.jpg',
'style_image': 'styles/farm-painting.jpg',
