doodle.py 文件源码

def setup_model(self, input=None):
        """Use lasagne to create a network of convolution layers, first using VGG19 as the framework
        and then adding augmentations for Semantic Style Transfer.
        """
        net, self.channels = {}, {}

        # Primary network for the main image. These are convolution only, and stop at layer 4_2 (rest unused).
        net['img']     = input or InputLayer((None, 3, None, None))
        net['conv1_1'] = ConvLayer(net['img'],     64, 3, pad=1)
        net['conv1_2'] = ConvLayer(net['conv1_1'], 64, 3, pad=1)
        net['pool1']   = PoolLayer(net['conv1_2'], 2, mode='average_exc_pad')
        net['conv2_1'] = ConvLayer(net['pool1'],   128, 3, pad=1)
        net['conv2_2'] = ConvLayer(net['conv2_1'], 128, 3, pad=1)
        net['pool2']   = PoolLayer(net['conv2_2'], 2, mode='average_exc_pad')
        net['conv3_1'] = ConvLayer(net['pool2'],   256, 3, pad=1)
        net['conv3_2'] = ConvLayer(net['conv3_1'], 256, 3, pad=1)
        net['conv3_3'] = ConvLayer(net['conv3_2'], 256, 3, pad=1)
        net['conv3_4'] = ConvLayer(net['conv3_3'], 256, 3, pad=1)
        net['pool3']   = PoolLayer(net['conv3_4'], 2, mode='average_exc_pad')
        net['conv4_1'] = ConvLayer(net['pool3'],   512, 3, pad=1)
        net['conv4_2'] = ConvLayer(net['conv4_1'], 512, 3, pad=1)
        net['conv4_3'] = ConvLayer(net['conv4_2'], 512, 3, pad=1)
        net['conv4_4'] = ConvLayer(net['conv4_3'], 512, 3, pad=1)
        net['pool4']   = PoolLayer(net['conv4_4'], 2, mode='average_exc_pad')
        net['conv5_1'] = ConvLayer(net['pool4'],   512, 3, pad=1)
        net['conv5_2'] = ConvLayer(net['conv5_1'], 512, 3, pad=1)
        net['conv5_3'] = ConvLayer(net['conv5_2'], 512, 3, pad=1)
        net['conv5_4'] = ConvLayer(net['conv5_3'], 512, 3, pad=1)
        net['main']    = net['conv5_4']

        # Auxiliary network for the semantic layers, and the nearest neighbors calculations.
        net['map'] = InputLayer((1, 1, None, None))
        for j, i in itertools.product(range(5), range(4)):
            if j < 2 and i > 1: continue
            suffix = '%i_%i' % (j+1, i+1)

            if i == 0:
                net['map%i'%(j+1)] = PoolLayer(net['map'], 2**j, mode='average_exc_pad')
            self.channels[suffix] = net['conv'+suffix].num_filters

            if args.semantic_weight > 0.0:
                net['sem'+suffix] = ConcatLayer([net['conv'+suffix], net['map%i'%(j+1)]])
            else:
                net['sem'+suffix] = net['conv'+suffix]

            net['dup'+suffix] = InputLayer(net['sem'+suffix].output_shape)
            net['nn'+suffix] = ConvLayer(net['dup'+suffix], 1, 3, b=None, pad=0, flip_filters=False)

        self.network = net