我用Chainer编写了这段代码，我想迁移到Keras。
class UNet(Chain):
def __init__(self):
super(UNet, self).__init__()
with self.init_scope():
self.conv1 = L.Convolution2D(1, 16, 4, 2, 1)
self.norm1 = L.BatchNormalization(16)
self.conv2 = L.Convolution2D(16, 32, 4, 2, 1)
self.norm2 = L.BatchNormalization(32)
self.conv3 = L.Convolution2D(32, 64, 4, 2, 1)
self.norm3 = L.BatchNormalization(64)
self.conv4 = L.Convolution2D(64, 128, 4, 2, 1)
self.norm4 = L.BatchNormalization(128)
self.conv5 = L.Convolution2D(128, 256, 4, 2, 1)
self.norm5 = L.BatchNormalization(256)
self.conv6 = L.Convolution2D(256, 512, 4, 2, 1)
self.norm6 = L.BatchNormalization(512)
self.deconv1 = L.Deconvolution2D(512, 256, 4, 2, 1)
self.denorm1 = L.BatchNormalization(256)
self.deconv2 = L.Deconvolution2D(512, 128, 4, 2, 1)
self.denorm2 = L.BatchNormalization(128)
self.deconv3 = L.Deconvolution2D(256, 64, 4, 2, 1)
self.denorm3 = L.BatchNormalization(64)
self.deconv4 = L.Deconvolution2D(128, 32, 4, 2, 1)
self.denorm4 = L.BatchNormalization(32)
self.deconv5 = L.Deconvolution2D(64, 16, 4, 2, 1)
self.denorm5 = L.BatchNormalization(16)
self.deconv6 = L.Deconvolution2D(32, 1, 4, 2, 1)
def __call__(self, X):
h1 = F.leaky_relu(self.norm1(self.conv1(X)))
h2 = F.leaky_relu(self.norm2(self.conv2(h1)))
h3 = F.leaky_relu(self.norm3(self.conv3(h2)))
h4 = F.leaky_relu(self.norm4(self.conv4(h3)))
h5 = F.leaky_relu(self.norm5(self.conv5(h4)))
h6 = F.leaky_relu(self.norm6(self.conv6(h5)))
dh = F.relu(F.dropout(self.denorm1(self.deconv1(h6))))
dh = F.relu(F.dropout(self.denorm2(self.deconv2(F.concat((dh, h5))))))
dh = F.relu(F.dropout(self.denorm3(self.deconv3(F.concat((dh, h4))))))
dh = F.relu(self.denorm4(self.deconv4(F.concat((dh, h3)))))
dh = F.relu(self.denorm5(self.deconv5(F.concat((dh, h2)))))
dh = F.sigmoid(self.deconv6(F.concat((dh, h1))))
return dh
我正在实现用于图像转换的Unet体系结构，但是，我正在用于音乐源分离。 我不知道将输入通道和输出放在keras conv2d方法中。
预先感谢