class CryptoNet_fivelayer(Module):
def __init__(self, in_dim, n_class):
super(CryptoNet_fivelayer, self).__init__()
self.conv = ConvLayer(in_dim, 5, 5,5, zero_padding=1, stride=2, method='SAME')
self.sq1 = Activators.Square()
self.fc1 = FullyConnect(845, 100)
self.sq2 = Activators.Square()
self.fc2 = FullyConnect(100, n_class)
self.logsoftmax = Logsoftmax()
def forward(self, x):
in_size = x.shape[0]
out_1 = self.sq1.forward(self.conv.forward(x))
self.conv_out_shape = out_1.shape
# print('out1shape: ',self.conv_out_shape)
out_1 = out_1.reshape(in_size, -1) # 将输出拉成一行
out_2 = self.sq2.forward(self.fc1.forward(out_1))
out_3 = self.fc2.forward(out_2)
out_logsoftmax = self.logsoftmax.forward(out_3)
return out_logsoftmax
def backward(self, dy):
dy_logsoftmax = self.logsoftmax.gradient(dy)
dy_f3 = self.fc2.gradient(dy_logsoftmax)
dy_f2 = self.fc1.gradient(self.sq2.gradient(dy_f3))
dy_f2 = dy_f2.reshape(self.conv_out_shape)
self.conv.gradient(self.sq1.gradient(dy_f2))
class Discriminator(Module):
def __init__(self):
super(Discriminator, self).__init__()
# 输入1*28*28 MNIST
# 1*28*28 -> 64*16*16
self.conv1 = ConvLayer(nc, ndf, 4,4, zero_padding=1, stride=2,method='SAME', bias_required=False)
self.lrelu1 = Activators.LeakyReLU(0.2)
# 64*16*16 -> 128*8*8
self.conv2 = ConvLayer(ndf, ndf*2, 4,4, zero_padding=1, stride=2, method='SAME', bias_required=False)
self.bn1 = BatchNorm(ndf*2)
self.lrelu2 = Activators.LeakyReLU(0.2)
# 128*8*8 -> 256*4*4
self.conv3 = ConvLayer(ndf*2, ndf*4, 4,4, zero_padding=1, stride=2, method='SAME', bias_required=False)
self.bn2 = BatchNorm(ndf*4)
self.lrelu3 = Activators.LeakyReLU(0.2)
# 256*4*4 -> 1*1
self.conv4 = ConvLayer(ndf*4, 1, 4,4, zero_padding=0, stride=1, method='VALID', bias_required=False)
self.sigmoid = Activators.Sigmoid_CE()
def forward(self, x_input):
l1 = self.lrelu1.forward(self.conv1.forward(x_input))
l2 = self.lrelu2.forward(self.bn1.forward(self.conv2.forward(l1)))
l3 = self.lrelu3.forward(self.bn2.forward(self.conv3.forward(l2)))
l4 = self.conv4.forward(l3)
# print('D l1 shape: ',l1.shape)
# print('D l2 shape: ',l2.shape)
# print('D l3 shape: ',l3.shape)
# print('D l4 shape: ',l4.shape)
output_sigmoid = self.sigmoid.forward(l4)
return output_sigmoid
def backward(self, dy):
# print('dy.shape: ', dy.shape)
dy_sigmoid = self.sigmoid.gradient(dy)
# print('dy_sigmoid.shape: ', dy_sigmoid.shape)
dy_l4 = self.conv4.gradient(dy_sigmoid)
dy_l3 = self.conv3.gradient(self.bn2.gradient(self.lrelu3.gradient(dy_l4)))
dy_l2 = self.conv2.gradient(self.bn1.gradient(self.lrelu2.gradient(dy_l3)))
dy_l1 = self.conv1.gradient(self.lrelu1.gradient(dy_l2))
# print('D_backward output shape: ',dy_l1.shape)
return dy_l1
class Lenet_numpy(Module):
def __init__(self, in_dim, n_class):
super(Lenet_numpy, self).__init__()
self.conv1 = ConvLayer(in_dim, 6, 5,5, zero_padding=2, stride=1, method='SAME')
self.conv2 = ConvLayer(6, 16, 5,5, zero_padding=0, stride=1, method='VALID')
self.conv3 = ConvLayer(16, 120, 5,5, zero_padding=0, stride=1, method='VALID')
self.maxpool1 = MaxPooling(pool_shape=(2,2), stride=(2,2))
self.maxpool2 = MaxPooling(pool_shape=(2,2), stride=(2,2))
self.relu1 = ReLU()
self.relu2 = ReLU()
self.relu3 = ReLU()
self.relu4 = ReLU()
self.fc1 = FullyConnect(120, 84)
self.fc2 = FullyConnect(84, n_class)
self.logsoftmax = Logsoftmax()
def forward(self, x): # 存在问题是：同一个对象其实是不能多次使用的，因为每个对象都有自己的input和output，如果重复使用反向会错误
in_size = x.shape[0]
out_c1s2 = self.relu1.forward(self.maxpool1.forward(self.conv1.forward(x)))
out_c3s4 = self.relu2.forward(self.maxpool2.forward(self.conv2.forward(out_c1s2)))
out_c5 = self.relu3.forward(self.conv3.forward(out_c3s4))
self.conv_out_shape = out_c5.shape
out_c5 = out_c5.reshape(in_size, -1)
out_f6 = self.relu4.forward(self.fc1.forward(out_c5))
out_f7 = self.fc2.forward(out_f6)
out_logsoftmax = self.logsoftmax.forward(out_f7)
return out_logsoftmax
def backward(self, dy):
dy_logsoftmax = self.logsoftmax.gradient(dy)
dy_f7 = self.fc2.gradient(dy_logsoftmax)
dy_f6 = self.fc1.gradient(self.relu4.gradient(dy_f7))
dy_f6 = dy_f6.reshape(self.conv_out_shape)
dy_c5 = self.conv3.gradient(self.relu3.gradient(dy_f6))
dy_c3f4 = self.conv2.gradient(self.maxpool2.gradient(self.relu2.gradient(dy_c5)))
self.conv1.gradient(self.maxpool1.gradient(self.relu1.gradient(dy_c3f4)))