深度学习中epoch与map的关系

在深度学习中，epoch是指将整个训练集数据完整地过一遍的次数。而map（mean average precision）是一种衡量分类算法性能的指标，用于衡量模型在不同类别上的表现。在训练深度学习模型时，我们可以通过多次迭代（即多个epoch）来训练模型，以提高模型的性能和泛化能力，进而提高map值。也可以通过调整模型的超参数来进一步提高map值。因此，epoch和map是密切相关的，epoch的增加可以对map值产生积极的影响。

相关问题

pycharm深度学习预测波士顿房价代码

以下是一个使用PyCharm编写的深度学习预测波士顿房价的代码，其中使用了神经网络模型和相关的科学计算库、数据交换格式包和绘图工具包：

# 导入相关库
import numpy as np
import json
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D

# 定义神经网络类
class Network(object):
    def __init__(self, sizes):
        self.num_layers = len(sizes)
        self.sizes = sizes
        self.biases = [np.zeros((y, 1)) for y in sizes[1:]]
        self.weights = [np.random.randn(y, x) for x, y in zip(sizes[:-1], sizes[1:])]

    def feedforward(self, a):
        for b, w in zip(self.biases, self.weights):
            a = sigmoid(np.dot(w, a) + b)
        return a

    def SGD(self, training_data, epochs, mini_batch_size, eta, test_data=None):
        if test_data: n_test = len(test_data)
        n = len(training_data)
        for j in range(epochs):
            np.random.shuffle(training_data)
            mini_batches = [training_data[k:k+mini_batch_size] for k in range(0, n, mini_batch_size)]
            for mini_batch in mini_batches:
                self.update_mini_batch(mini_batch, eta)
            if test_data:
                print("Epoch {0}: {1} / {2}".format(j, self.evaluate(test_data), n_test))
            else:
                print("Epoch {0} complete".format(j))

    def update_mini_batch(self, mini_batch, eta):
        nabla_b = [np.zeros(b.shape) for b in self.biases]
        nabla_w = [np.zeros(w.shape) for w in self.weights]
        for x, y in mini_batch:
            delta_nabla_b, delta_nabla_w = self.backprop(x, y)
            nabla_b = [nb+dnb for nb, dnb in zip(nabla_b, delta_nabla_b)]
            nabla_w = [nw+dnw for nw, dnw in zip(nabla_w, delta_nabla_w)]
        self.weights = [w-(eta/len(mini_batch))*nw for w, nw in zip(self.weights, nabla_w)]
        self.biases = [b-(eta/len(mini_batch))*nb for b, nb in zip(self.biases, nabla_b)]

    def backprop(self, x, y):
        nabla_b = [np.zeros(b.shape) for b in self.biases]
        nabla_w = [np.zeros(w.shape) for w in self.weights]
        activation = x
        activations = [x]
        zs = []
        for b, w in zip(self.biases, self.weights):
            z = np.dot(w, activation)+b
            zs.append(z)
            activation = sigmoid(z)
            activations.append(activation)
        delta = self.cost_derivative(activations[-1], y) * sigmoid_prime(zs[-1])
        nabla_b[-1] = delta
        nabla_w[-1] = np.dot(delta, activations[-2].transpose())
        for l in range(2, self.num_layers):
            z = zs[-l]
            sp = sigmoid_prime(z)
            delta = np.dot(self.weights[-l+1].transpose(), delta) * sp
            nabla_b[-l] = delta
            nabla_w[-l] = np.dot(delta, activations[-l-1].transpose())
        return (nabla_b, nabla_w)

    def evaluate(self, test_data):
        test_results = [(np.argmax(self.feedforward(x)), y) for (x, y) in test_data]
        return sum(int(x == y) for (x, y) in test_results)

    def cost_derivative(self, output_activations, y):
        return (output_activations-y)

# 定义sigmoid函数和其导数
def sigmoid(z):
    return 1.0/(1.0+np.exp(-z))

def sigmoid_prime(z):
    return sigmoid(z)*(1-sigmoid(z))

# 加载数据集
with open('housing.data', 'r') as f:
    data = f.readlines()
    data = [list(map(float, x.strip().split())) for x in data]
    data = [(np.array(x[:-1]).reshape(13, 1), x[-1]) for x in data]

# 划分训练集和测试集
training_data, test_data = data[:-10], data[-10:]

# 初始化神经网络
net = Network([13, 5, 1])

# 训练神经网络
net.SGD(training_data, 1000, 10, 0.5, test_data=test_data)

# 绘制预测结果
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
x = [x[0][0] for x in test_data]
y = [x[0][1] for x in test_data]
z = [x[1] for x in test_data]
ax.scatter(x, y, z, c='r', marker='o')
x = np.arange(0, 1, 0.1)
y = np.arange(0, 1, 0.1)
x, y = np.meshgrid(x, y)
z = np.array([net.feedforward(np.array([xi, yi]).reshape(2, 1))[0][0] for xi, yi in zip(x, y)])
ax.plot_surface(x, y, z)
ax.set_xlabel('X Label')
ax.set_ylabel('Y Label')
ax.set_zlabel('Z Label')
plt.show()

深度学习实现中文情感分析从获取数据集、预处理、构建模型、训练模型和测试模型的代码

获取数据集：

import pandas as pd

# 读取csv文件
df = pd.read_csv('data.csv', encoding='utf-8')
# 选择需要的列
df = df[['text', 'label']]
# 将标签转换为数字
df['label'] = df['label'].map({'positive': 1, 'negative': 0})

预处理：

import jieba

# 分词
def cut_text(text):
    return ' '.join(jieba.cut(text))

# 对文本进行分词
df['text'] = df['text'].apply(cut_text)

构建模型：

import torch
from torch import nn
from transformers import BertTokenizer, BertModel

class SentimentModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.bert = BertModel.from_pretrained('bert-base-chinese')
        self.fc = nn.Linear(768, 2)
        self.softmax = nn.Softmax(dim=1)

    def forward(self, x):
        _, pooled = self.bert(x)
        out = self.fc(pooled)
        out = self.softmax(out)
        return out

tokenizer = BertTokenizer.from_pretrained('bert-base-chinese')
model = SentimentModel()

训练模型：

from torch.utils.data import DataLoader, Dataset
import torch.optim as optim

class SentimentDataset(Dataset):
    def __init__(self, df, tokenizer):
        self.df = df
        self.tokenizer = tokenizer

    def __len__(self):
        return len(self.df)

    def __getitem__(self, idx):
        text = self.df.iloc[idx]['text']
        label = self.df.iloc[idx]['label']

        inputs = self.tokenizer.encode_plus(
            text,
            add_special_tokens=True,
            max_length=256,
            padding='max_length',
            truncation=True,
            return_attention_mask=True,
            return_tensors='pt'
        )

        return inputs['input_ids'], inputs['attention_mask'], torch.tensor(label)

def train(model, train_loader):
    optimizer = optim.Adam(model.parameters(), lr=1e-5)
    criterion = nn.CrossEntropyLoss()

    model.train()

    for epoch in range(10):
        for i, (input_ids, attention_mask, label) in enumerate(train_loader):
            optimizer.zero_grad()

            logits = model(input_ids=input_ids, attention_mask=attention_mask)
            loss = criterion(logits, label)

            loss.backward()
            optimizer.step()

            if i % 100 == 0:
                print('Epoch: {}/{} | Batch: {}/{} | Loss: {:.4f}'.format(
                    epoch+1, 10, i+1, len(train_loader), loss.item()))

train_dataset = SentimentDataset(df_train, tokenizer)
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)

train(model, train_loader)

测试模型：

def predict(model, text):
    inputs = tokenizer.encode_plus(
        text,
        add_special_tokens=True,
        max_length=256,
        padding='max_length',
        truncation=True,
        return_attention_mask=True,
        return_tensors='pt'
    )

    logits = model(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'])
    probs = nn.Softmax(dim=1)(logits)

    return probs.detach().numpy()[0]

text = '这部电影真的很好看，值得一看！'
probs = predict(model, text)
print('Positive probability:', probs[1])