DataWhale team punch learning camp task01-3

Multilayer Perceptron

MLP implementation from scratch

import torch
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)

Get the training set

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size,root='/home/kesci/input/FashionMNIST2065')

The definition of the model parameters

num_inputs, num_outputs, num_hiddens = 784, 10, 256

W1 = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_hiddens)), dtype=torch.float)
b1 = torch.zeros(num_hiddens, dtype=torch.float)
W2 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_outputs)), dtype=torch.float)
b2 = torch.zeros(num_outputs, dtype=torch.float)

params = [W1, b1, W2, b2]
for param in params:
    param.requires_grad_(requires_grad=True)

Define Activation function

def relu(X):
    return torch.max(input=X, other=torch.tensor(0.0))

Defining network

def net(X):
    X = X.view((-1, num_inputs))
    H = relu(torch.matmul(X, W1) + b1)
    return torch.matmul(H, W2) + b2

Defined loss function

loss = torch.nn.CrossEntropyLoss()

training

num_epochs, lr = 5, 100.0
# def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
#               params=None, lr=None, optimizer=None):
#     for epoch in range(num_epochs):
#         train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
#         for X, y in train_iter:
#             y_hat = net(X)
#             l = loss(y_hat, y).sum()
#             
#             # 梯度清零
#             if optimizer is not None:
#                 optimizer.zero_grad()
#             elif params is not None and params[0].grad is not None:
#                 for param in params:
#                     param.grad.data.zero_()
#            
#             l.backward()
#             if optimizer is None:
#                 d2l.sgd(params, lr, batch_size)
#             else:
#                 optimizer.step()  # “softmax回归的简洁实现”一节将用到
#             
#             
#             train_l_sum += l.item()
#             train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
#             n += y.shape[0]
#         test_acc = evaluate_accuracy(test_iter, net)
#         print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
#               % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))

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

epoch 1, loss 0.0030, train acc 0.712, test acc 0.806
epoch 2, loss 0.0019, train acc 0.821, test acc 0.806
epoch 3, loss 0.0017, train acc 0.847, test acc 0.825
epoch 4, loss 0.0015, train acc 0.856, test acc 0.834
epoch 5, loss 0.0015, train acc 0.863, test acc 0.847

MLP pytorch achieve

import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

print(torch.__version__)

Initialize the model and various parameters

num_inputs, num_outputs, num_hiddens = 784, 10, 256
    
net = nn.Sequential(
        d2l.FlattenLayer(),
        nn.Linear(num_inputs, num_hiddens),
        nn.ReLU(),
        nn.Linear(num_hiddens, num_outputs), 
        )
    
for params in net.parameters():
    init.normal_(params, mean=0, std=0.01)

training

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size,root='/home/kesci/input/FashionMNIST2065')
loss = torch.nn.CrossEntropyLoss()

optimizer = torch.optim.SGD(net.parameters(), lr=0.5)

num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)

epoch 1, loss 0.0031, train acc 0.701, test acc 0.774
epoch 2, loss 0.0019, train acc 0.821, test acc 0.806
epoch 3, loss 0.0017, train acc 0.841, test acc 0.805
epoch 4, loss 0.0015, train acc 0.855, test acc 0.834
epoch 5, loss 0.0014, train acc 0.866, test acc 0.840