当前位置: 首页 > news >正文

第七章 验收手写数字识别

# ==================================================================================
# 10_11验收手写数字识别
# ==========# 在解耦和验收测试集图片和标签处理上仍有较大优化空间# 导入相关库
import numpy as np
import os
import struct
import pickle
import cv2# 定义导入函数
def load_images(path):with open(path, "rb") as f:data = f.read()magic_number, num_items, rows, cols = struct.unpack(">iiii", data[:16])return np.asanyarray(bytearray(data[16:]), dtype=np.uint8).reshape(num_items, 28, 28)def load_labels(path):with open(path, "rb") as f:data = f.read()return np.asanyarray(bytearray(data[8:]), dtype=np.int32)# 激活函数
# 定义sigmoid函数
def sigmoid(x):result = np.zeros_like(x)positive_mask = x >= 0result[positive_mask] = 1 / (1 + np.exp(-x[positive_mask]))negative_mask = x < 0exp_x = np.exp(x[negative_mask])result[negative_mask] = exp_x / (1 + exp_x)return result# 定义softmax函数
def softmax(x):max_x = np.max(x, axis=-1, keepdims=True)x = x - max_xex = np.exp(x)sum_ex = np.sum(ex, axis=1, keepdims=True)result = ex / sum_exresult = np.clip(result, 1e-10, 1e10)return result# 训练集编码处理
# 定义独热编码函数
def make_onehot(labels, class_num):result = np.zeros((labels.shape[0], class_num))for idx, cls in enumerate(labels):result[idx, cls] = 1return result# 定义dataset类
class Dataset:def __init__(self, all_images, all_labels):self.all_images = all_imagesself.all_labels = all_labelsdef __getitem__(self, index):image = self.all_images[index]label = self.all_labels[index]return image, labeldef __len__(self):return len(self.all_images)# 定义dataloader类
class DataLoader:def __init__(self, dataset, batch_size, shuffle=True):self.dataset = datasetself.batch_size = batch_sizeself.shuffle = shuffleself.idx = np.arange(len(self.dataset))def __iter__(self):# 如果需要打乱,则在每个 epoch 开始时重新排列索引if self.shuffle:np.random.shuffle(self.idx)self.cursor = 0return selfdef __next__(self):if self.cursor >= len(self.dataset):raise StopIteration# 使用索引来获取数据batch_idx = self.idx[self.cursor : min(self.cursor + self.batch_size, len(self.dataset))]batch_images = self.dataset.all_images[batch_idx]batch_labels = self.dataset.all_labels[batch_idx]self.cursor += self.batch_sizereturn batch_images, batch_labels# 父类Module,查看各层结构
# 定义Module类
class Module:def __init__(self):self.info = "Module:/n"self.params = []def __repr__(self):return self.info# 定义Parameter类
class Parameter:def __init__(self, weight):self.weight = weightself.grad = np.zeros_like(weight)self.velocity = np.zeros_like(weight)  # 🆕 新增:动量/速度向量# 定义linear类
class Linear(Module):def __init__(self, in_features, out_features):super().__init__()self.info += f"**    Linear({in_features}, {out_features})"# 🆕 修正:使用 He 初始化,适用于 ReLUstd_test = np.sqrt(2 / in_features)# 使用 std_test 来初始化权重self.W = Parameter(np.random.normal(0, std_test, size=(in_features, out_features)))# 偏置 B 最好初始化为 0,而非随机值self.B = Parameter(np.zeros((1, out_features)))self.params.append(self.W)self.params.append(self.B)def forward(self, x):self.x = xreturn np.dot(x, self.W.weight) + self.B.weightdef backward(self, G):self.W.grad = np.dot(self.x.T, G)self.B.grad = np.mean(G, axis=0, keepdims=True)return np.dot(G, self.W.weight.T)# 定义Conv2D类
class Conv2D(Module):def __init__(self, in_channel, out_channel):super(Conv2D, self).__init__()self.info += f"     Conv2D({in_channel, out_channel})"std_test = np.sqrt(2 / in_channel)self.W = Parameter(np.random.normal(0, std_test, size=(in_channel, out_channel)))self.B = Parameter(np.zeros((1, out_channel)))self.params.append(self.W)self.params.append(self.B)def forward(self, x):result = x @ self.W.weight + self.B.weightself.x = xreturn resultdef backward(self, G):self.W.grad = self.x.T @ Gself.B.grad = np.mean(G, axis=0, keepdims=True)delta_x = G @ self.W.weight.Treturn delta_x# 定义Conv1D类
class Conv1D(Module):def __init__(self, in_channel, out_channel):super(Conv1D, self).__init__()self.info += f"     Conv1D({in_channel,out_channel})"self.W = Parameter(np.random.normal(0, 1, size=(in_channel, out_channel)))self.B = Parameter(np.zeros((1, out_channel)))self.params.append(self.W)self.params.append(self.B)def forward(self, x):result = x @ self.W.weight + self.B.weightself.x = xreturn resultdef backward(self, G):self.W.grad = self.x.T @ Gself.B.grad = np.mean(G, axis=0, keepdims=True)delta_x = G @ self.W.weight.Treturn delta_x# 优化器的父类
# 定义Optimizer类
class Optimizer:def __init__(self, parameters, lr):self.parameters = parametersself.lr = lrdef zero_grad(self):for p in self.parameters:p.grad.fill(0)# 定义SGD类,学习率较大
class SGD(Optimizer):def step(self):for p in self.parameters:p.weight -= self.lr * p.grad# 定义MSGD类,学习率较大
class MSGD(Optimizer):def __init__(self, parameters, lr, u):super().__init__(parameters, lr)self.u = udef step(self):for p in self.parameters:# 1. 更新速度 V_t = u * V_{t-1} + p.gradp.velocity = self.u * p.velocity + p.grad# 2. 更新权重 W = W - lr * V_tp.weight -= self.lr * p.velocity# 定义Adam类,学习率一般较小10^-3到10^-6
class Adam(Optimizer):def __init__(self, parameters, lr, beta1=0.9, beta2=0.999, e=1e-8):super().__init__(parameters, lr)self.beta1 = beta1self.beta2 = beta2self.e = eself.t = 0for p in self.parameters:# p.m = 0p.m = np.zeros_like(p.weight)# p.v = 0p.v = np.zeros_like(p.weight)def step(self):self.t += 1for p in self.parameters:gt = p.gradp.m = self.beta1 * p.m + (1 - self.beta1) * gtp.v = self.beta2 * p.v + (1 - self.beta2) * gt**2mt_ = p.m / (1 - self.beta1**self.t)vt_ = p.v / (1 - self.beta2**self.t)p.weight = p.weight - self.lr * mt_ / np.sqrt(vt_ + self.e)# 定义Sigmoid类
class Sigmoid(Module):def __init__(self):super().__init__()self.info += "**    Sigmoid()"  # 打印信息def forward(self, x):self.result = sigmoid(x)return self.resultdef backward(self, G):return G * self.result * (1 - self.result)# 定义Tanh类
class Tanh(Module):def __init__(self):super().__init__()self.info += "**    Tanh()"  # 打印信息def forward(self, x):self.result = 2 * sigmoid(2 * x) - 1return self.resultdef backward(self, G):return G * (1 - self.result**2)# 定义Softmax类
class Softmax(Module):def __init__(self):super().__init__()self.info += "**    Softmax()"  # 打印信息def forward(self, x):self.p = softmax(x)return self.pdef backward(self, G):G = (self.p - G) / len(G)return G# 定义ReLU类
class ReLU(Module):def __init__(self):super().__init__()self.info += "**    ReLU()"  # 打印信息def forward(self, x):self.x = xreturn np.maximum(0, x)def backward(self, G):grad = G.copy()grad[self.x <= 0] = 0return grad# 定义Dropout类class Dropout(Module):def __init__(self, p=0.3):super().__init__()self.info += f"**    Dropout(p={p})"  # 打印信息self.p = pself.is_training = True  # 🆕 新增:训练状态标志def forward(self, x):if not self.is_training:return x  # 评估时直接返回r = np.random.rand(*x.shape)self.mask = r >= self.p  # 创建掩码# 应用掩码和缩放return (x * self.mask) / (1 - self.p)def backward(self, G):if not self.is_training:return G  # 评估时直接返回梯度G[~self.mask] = 0return G / (1 - self.p)# 定义ModelList类
class ModelList:def __init__(self, layers):self.layers = layersdef forward(self, x):for layer in self.layers:x = layer.forward(x)return xdef backward(self, G):for layer in self.layers[::-1]:G = layer.backward(G)def __repr__(self):info = ""for layer in self.layers:info += layer.info + "/n"return info# 定义Model类
class Model:def __init__(self):self.model_list = ModelList([Linear(784, 512),ReLU(),Dropout(0.2),Conv2D(512, 256),Tanh(),Dropout(0.1),Linear(256, 10),Softmax(),])def forward(self, x, label=None):pre = self.model_list.forward(x)if label is not None:self.label = labelloss = -np.mean(self.label * np.log(pre))return losselse:return np.argmax(pre, axis=-1)def backward(self):self.model_list.backward(self.label)def train(self):"""设置模型为训练模式 (启用 Dropout)。"""for layer in self.model_list.layers:# 检查层是否有 is_training 属性 (即只针对 Dropout 层)if hasattr(layer, "is_training"):layer.is_training = Truedef eval(self):"""设置模型为评估/推理模式 (禁用 Dropout)。"""for layer in self.model_list.layers:if hasattr(layer, "is_training"):layer.is_training = Falsedef __repr__(self):return self.model_list.__repr__()def parameter(self):all_Parameter = []for layer in self.model_list.layers:all_Parameter.extend(layer.params)return all_Parameter# 主函数
if __name__ == '__main__':# 加载数据with open('D:/my code/0.9838.pkl', 'rb') as f:model=pickle.load(f)root_path='D:/my code/Python/NLP basic/data/test_images'#测试图片根路径images_file=os.listdir('D:/my code/Python/NLP basic/data/test_images')#测试图片文件名列表test_images=np.zeros((len(images_file),784))#初始化测试图片矩阵test_labels=np.zeros((len(images_file),1))#初始化测试标签矩阵for fi,image in enumerate(images_file):#遍历测试图片,fi为图片序号path=os.path.join(root_path,image)#测试图片路径img=cv2.imread(path)#读取测试图片img_gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)#灰度化img=cv2.resize(img_gray,(28,28))#缩放为28*28test_images[fi]=img.reshape(-1)#将图片矩阵展平并赋值给测试图片矩阵test_labels[fi]=int(image[-5:-4])#获取图片标签并赋值给测试标签矩阵batch_size = 1test_dataset = Dataset(test_images, test_labels)test_dataloader = DataLoader(test_dataset, batch_size)right_num = 0for x, batch_labels in test_dataloader:pre_idx = model.forward(x)right_num += np.sum(pre_idx == batch_labels)  # 统计正确个数acc = right_num / len(test_images)  # 计算准确率print(acc)

image

image

http://www.hskmm.com/?act=detail&tid=28848

相关文章:

  • 2025保洁公司权威推荐:上海恒旺保洁服务,口碑与实力兼备!
  • 初识pytorch:深度学习中关于数据加载的Dataset和DataLoader
  • 中考_学科
  • 2025卧式CNC高压清洗机厂家推荐榜:高效清洁与卓越性能首
  • 2025年深水搅拌机曝气机优质供应商推荐品牌/源头工厂/哪家好?
  • 工具篇-Cursor中接入DeepSeek,只要这三步
  • 2025年中医确有专长培训TOP5榜单:权威认证与实战经验结
  • .NET 记录Amazon上传S3异常问题
  • 求职信 - MKT
  • Linux中tar、zip、gz、rar文件 解压缩归类
  • PostgreSQL多节点部署分布式数据库之Citus
  • 2025气柱袋厂家最新推荐榜:包装防护与性价比之选!
  • java项目CPU爆高问题排查方案
  • 2025实验室净化优质厂家推荐:华锐净化专业定制,洁净空间首
  • 小九源码-springboot051-智能推荐旅游平台 - 实践
  • 2025方钢供应厂家推荐:山东鑫泽金属制品优质选择!
  • 2025年中国行业内领先的GEO(AI搜索优化)厂家权威推荐榜单:四川云视GEO当首
  • 【vLLM】使用vLLM部署Qwen3-VL-30B-A3B-Instruct
  • 2025 屋顶防水维修/外墙防水维修/电梯井防水维修厂家推荐榜:专注全场景渗漏解决方案供应!
  • 2025 流化床/GMP标准/实验室气流粉碎机厂家推荐榜:聚焦多行业粉碎需求,赋能高效生产!
  • 2025年OPP涂布机源头厂家最新推荐榜:技术领先与市场口碑
  • 【EBS】EBS系统新克隆环境的MRP无法运行
  • 花纹铝板口碑推荐/铝板厂家推荐/铝板知名品牌
  • FirstOrDefault
  • 正则表达式详解
  • 2025通风气楼厂家推荐:欧诺通风设备,高效节能品质之选
  • 2025年湖南短视频代运营/拍摄/剪辑/方案策划/推广/引流/IP打造公司综合实力排行榜推荐
  • 2025粉末涂料厂家推荐:财诺名荣,环保高效品质之选!
  • 2025.10.11NOIP模拟
  • 颠覆传统RAG!Agentic RAG登场,AI代理如何“自我进化”解决复杂 query?