MXNET：多層感知機

標籤：attach   initial   瞭解   port   rate   net   dde   learn   ati   

從零開始

前面瞭解了多層感知機的原理，我們來實現一個多層感知機。

# -*- coding: utf-8 -*-from mxnet import initfrom mxnet import ndarray as ndfrom mxnet.gluon import loss as glossimport gb# 定義資料來源batch_size = 256train_iter, test_iter = gb.load_data_fashion_mnist(batch_size)# 定義模型參數num_inputs = 784num_outputs = 10num_hiddens = 256W1 = 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()# 定義啟用函數def relu(X):    return nd.maximum(X, 0)# 定義模型def net(X):    X = X.reshape((-1, num_inputs))    H = relu(nd.dot(X, W1) + b1)    return nd.dot(H, W2) + b2# 定義損失函數loss = gloss.SoftmaxCrossEntropyLoss()# 訓練模型num_epochs = 5lr = 0.5gb.train_cpu(net, train_iter, test_iter, loss, num_epochs, batch_size,             params, lr)

添加隱層後，模型的效能大幅提升

# outputepoch 1, loss 0.5029, train acc 0.852, test acc 0.934epoch 2, loss 0.2000, train acc 0.943, test acc 0.956epoch 3, loss 0.1431, train acc 0.959, test acc 0.964epoch 4, loss 0.1138, train acc 0.967, test acc 0.968epoch 5, loss 0.0939, train acc 0.973, test acc 0.973

在定義模型參數和定義模型步驟，仍然有一些繁瑣。

使用Gluon

# -*- coding: utf-8 -*-from mxnet import initfrom mxnet import ndarray as ndfrom mxnet.gluon import loss as glossimport gb# 定義資料來源batch_size = 256train_iter, test_iter = gb.load_data_fashion_mnist(batch_size)# 定義模型from mxnet.gluon import nnnet = nn.Sequential()net.add(nn.Dense(256, activation='relu'))net.add(nn.Dense(10))net.add(nn.Dense(10))net.initialize(init.Normal(sigma=0.01))# 定義損失函數loss = gloss.SoftmaxCrossEntropyLoss()# 訓練模型from mxnet import gluontrainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.5})num_epochs = 5gb.train_cpu(net, train_iter, test_iter, loss, num_epochs, batch_size,             None, None, trainer)# outputepoch 1, loss 1.3065, train acc 0.525, test acc 0.814epoch 2, loss 0.2480, train acc 0.928, test acc 0.950epoch 3, loss 0.1442, train acc 0.958, test acc 0.961epoch 4, loss 0.1060, train acc 0.969, test acc 0.971epoch 5, loss 0.0807, train acc 0.976, test acc 0.973

MXNET：多層感知機