# 手寫數字識別
import torch
# 資料集處理
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import dataloader
# 函式 啟用函式等
import torch.nn.functional as f
# 優化器包
import torch.optim as optim
# 分批
batch_size = 64
# 1. 資料處理
transform = transforms.compose([
transforms.totensor(),
transforms.normalize((0.1307, ), (0.3081, ))
])train_dataset = datasets.mnist(root='../dataset/mnist/',
train=true,
download=true,
transform=transform)
test_dataset = datasets.mnist(root='../dataset/mnist/',
train=false,
download=true,
transform=transform)
train_loader = dataloader(test_dataset,
shuffle=true,
batch_size=batch_size)
test_loader = dataloader(test_dataset,
shuffle=false,
batch_size=batch_size)
# 資料為1 * 28 * 28
# 2. 建立模型
class net(torch.nn.module):
def __init__(self):
super(net, self).__init__()
self.l1 = torch.nn.linear(784, 512)
self.l2 = torch.nn.linear(512, 256)
self.l3 = torch.nn.linear(256, 128)
self.l4 = torch.nn.linear(128, 64)
self.l5 = torch.nn.linear(64, 10)
def forward(self, x):
x = x.view(-1, 784)
x = f.relu(self.l1(x))
x = f.relu(self.l2(x))
x = f.relu(self.l3(x))
x = f.relu(self.l4(x))
return self.l5(x)
model = net()
# 3.損失函式和優化器 交叉熵損失
criterion = torch.nn.crossentropyloss()
optimizer = optim.sgd(model.parameters(), lr=0.01, momentum=0.5)
# 4.迴圈訓練
def train(epoch):
running_loss = 0.0
for batch_idx, data in enumerate(train_loader):
inputs, target = data
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, target)
loss.backward()
optimizer.step()
running_loss += loss.item()
print(batch_idx% 300)
if batch_idx % 300 == 0:
print('[%d,%d] loss: %.10f' % (epoch+1, batch_idx+1, running_loss / 300))
running_loss = 0.0
# 測試驗證
def test():
correct = 0
total = 0
with torch.no_grad(): # 不會再進行梯度
for data in test_loader:
images, labels = data
outputs = model(images)
_, predicted = torch.max(outputs.data, dim=1)
total+=labels.size(0)
correct+=(predicted==labels).sum().item()
print("accuracy on test set: %d %%" % (100 * correct / total))
# 程式入口處
if __name__ == '__main__':
for epoch in range(200):
train(epoch)
test()
print("訓練結束...")
Tensorflow 多分類問題
import requests import numpy as np 複製 r requests.get 複製 with open iris.data w as f f.write r.text 複製 import pandas as pd 複製 data pd.read csv iris.data...
XGBoost解決多分類問題
xgboost官方給的二分類問題的例子是區別蘑菇有無毒，資料集和 都可以在xgboost中的demo資料夾對應找到，我是用的anaconda安裝的xgboost，實現起來比較容易。唯一的梗就是在終端中執行所給命令 xgboost mushroom.conf 時會報錯，是路徑設定的問題，所以我乾脆把x...
手寫數字問題
import osos.environ tf cpp min log level 2 使tensorflow少列印一些不必要的資訊 import tensorflow.compat.v1 as tf from tensorflow import keras from tensorflow.keras...