《动手学深度学习》用PyCharm实现 学习笔记（4）3.9多层感知机的从零开始实现

代码

import d2lzh as d2l
from mxnet import nd
from mxnet.gluon import loss as gloss
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
num_inputs, num_outputs, num_hiddens = 784, 10, 256

W1 = nd.random.normal(scale=0.01, shape=(num_inputs, num_hiddens))
b1 = nd.zeros(num_hiddens)
W2 = nd.random.normal(scale=0.01, shape=(num_hiddens, num_outputs))
b2 = nd.zeros(num_outputs)
params = [W1, b1, W2, b2]

for param in params:
    param.attach_grad()

def relu(X):
    return nd.maximum(X, 0)

def net(X):
    X = X.reshape((-1, num_inputs))
    H = relu(nd.dot(X, W1) + b1)
    return nd.dot(H, W2) + b2

loss = gloss.SoftmaxCrossEntropyLoss()

num_epochs, lr = 5, 0.5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
              params, lr)

输出结果

epoch 1, loss 0.7824, train acc 0.709, test acc 0.819
epoch 2, loss 0.4791, train acc 0.822, test acc 0.833
epoch 3, loss 0.4261, train acc 0.844, test acc 0.813
epoch 4, loss 0.4060, train acc 0.850, test acc 0.862
epoch 5, loss 0.3737, train acc 0.861, test acc 0.868