def create_srcnn():
"""
waifu2xのSRCNNというモデルを参考に作ってみる
"""
return chainer.Sequential(
Conv2DActiv(in_channels=None, out_channels=32, ksize=3,
activ=lambda x: F.leaky_relu(x, 0.1), pad=1),
Conv2DActiv(in_channels=None, out_channels=32, ksize=3,
activ=lambda x: F.leaky_relu(x, 0.1), pad=1),
Conv2DActiv(in_channels=None, out_channels=64, ksize=3,
activ=lambda x: F.leaky_relu(x, 0.1), pad=1),
Conv2DActiv(in_channels=None, out_channels=64, ksize=3,
activ=lambda x: F.leaky_relu(x, 0.1), pad=1),
Conv2DActiv(in_channels=None, out_channels=128, ksize=3,
activ=lambda x: F.leaky_relu(x, 0.1), pad=1),
Conv2DActiv(in_channels=None, out_channels=128, ksize=3,
activ=lambda x: F.leaky_relu(x, 0.1), pad=1),
L.Convolution2D(in_channels=None, out_channels=3, ksize=3, pad=1)
)
def __init__(self,
n_class=None,
pretrained_model=None,
mean=None,
initialW=None,
initial_bias=None):
param, path = utils.prepare_pretrained_model(
{
'n_class': n_class,
'mean': mean
}, pretrained_model, self._models, {
'n_class': 1000,
'mean': _imagenet_mean
})
self.mean = param['mean']
if initialW is None:
# Employ default initializers used in the original paper.
initialW = normal.Normal(0.01)
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
initialW = constant.Zero()
kwargs = {'initialW': initialW, 'initial_bias': initial_bias}
super(VGG16, self).__init__()
with self.init_scope():
self.conv1_1 = Conv2DActiv(None, 64, 3, 1, 1, **kwargs)
self.conv1_2 = Conv2DActiv(None, 64, 3, 1, 1, **kwargs)
self.pool1 = _max_pooling_2d
self.conv2_1 = Conv2DActiv(None, 128, 3, 1, 1, **kwargs)
self.conv2_2 = Conv2DActiv(None, 128, 3, 1, 1, **kwargs)
self.pool2 = _max_pooling_2d
self.conv3_1 = Conv2DActiv(None, 256, 3, 1, 1, **kwargs)
self.conv3_2 = Conv2DActiv(None, 256, 3, 1, 1, **kwargs)
self.conv3_3 = Conv2DActiv(None, 256, 3, 1, 1, **kwargs)
self.pool3 = _max_pooling_2d
self.conv4_1 = Conv2DActiv(None, 512, 3, 1, 1, **kwargs)
self.conv4_2 = Conv2DActiv(None, 512, 3, 1, 1, **kwargs)
self.conv4_3 = Conv2DActiv(None, 512, 3, 1, 1, **kwargs)
self.pool4 = _max_pooling_2d
self.conv5_1 = Conv2DActiv(None, 512, 3, 1, 1, **kwargs)
self.conv5_2 = Conv2DActiv(None, 512, 3, 1, 1, **kwargs)
self.conv5_3 = Conv2DActiv(None, 512, 3, 1, 1, **kwargs)
self.pool5 = _max_pooling_2d
self.fc6 = Linear(None, 4096, **kwargs)
self.fc6_relu = relu
self.fc6_dropout = dropout
self.fc7 = Linear(None, 4096, **kwargs)
self.fc7_relu = relu
self.fc7_dropout = dropout
self.fc8 = Linear(None, param['n_class'], **kwargs)
self.prob = softmax
if path:
chainer.serializers.load_npz(path, self)