task2 3

卷积神经网络基础 二维卷积层将输入和卷积核做互相关运算,并加上一个标量偏置来得到输出。卷积层的模型参数包括卷积核和标量偏置。 1*2卷积层 conv2d = Conv2D(kernel_size=(1, 2)) step = 30 lr = 0.01 for i in range(step): Y_hat = conv2d(X) l = ((Y_hat - Y) ** 2).sum() l.backward() # 梯度下降 conv2d.weight.data -= lr * conv2d.weight.grad conv2d.bias.dat