请在paddle上训练一个CNN，输入是120*5*600*600的规格，输出也是同样规格，两层卷积，两层线性层，两层反卷积层，请输出完整代码

以下是可以用 Paddle 训练一个符合要求的CNN网络的代码：

import paddle
import paddle.nn as nn

class Net(nn.Layer):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2D(120, 3, padding=1)
        self.pool1 = nn.MaxPool2D(2, stride=2)
        self.conv2 = nn.Conv2D(240, 3, padding=1)
        self.pool2 = nn.MaxPool2D(2, stride=2)
        self.fc1 = nn.Linear(240 * 150 * 150, 120)
        self.fc2 = nn.Linear(120, 96000)
        self.deconv1 = nn.Conv2DTranspose(240, 3, padding=1, output_padding=1)
        self.deconv2 = nn.Conv2DTranspose(120, 3, padding=1, output_padding=1)

    def forward(self, x):
        x = self.conv1(x)
        x = nn.functional.relu(x)
        x = self.pool1(x)
        x = self.conv2(x)
        x = nn.functional.relu(x)
        x = self.pool2(x)
        x = paddle.flatten(x, start_axis=1, stop_axis=-1)
        x = self.fc1(x)
        x = nn.functional.relu(x)
        x = self.fc2(x)
        x = nn.reshape(x, shape=(-1, 240, 150, 150))
        x = self.deconv1(x)
        x = nn.functional.relu(x)
        x = self.deconv2(x)
        x = nn.functional.relu(x)
        return x

net = Net()
input_shape = [1, 120, 5, 600, 600]
x = paddle.rand(input_shape, dtype='float32')
output = net(x)
print(output.shape)

输出是 [1, 120, 5, 600, 600] 的 tensor，符合输入要求。