HBU深度学习实验6-前馈神经网络（2）

已于 2025-02-12 15:52:17 修改
阅读量355 收藏 4
点赞数 10
文章标签： 深度学习 神经网络 人工智能
于 2024-10-21 19:22:23 首次发布
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.youkuaiyun.com/ckh20040422/article/details/142985755
版权

nndl包的下载

链接：https://pan.baidu.com/s/1WvTC_O8WKImVyiqQMOZ-VA?pwd=abcd 
提取码：abcd 
--来自百度网盘超级会员V4的分享

1、数据集的构建

Moon1000数据集，其中训练集640条、验证集160条、测试集200条

该数据集的数据是从两个带噪音的弯月形状数据分布中采样得到，每个样本包含2个特征。

from nndl.dataset import make_moons
# 采样1000个样本
n_samples = 1000
X, y = make_moons(n_samples=n_samples, shuffle=True, noise=0.1)

num_train = 640
num_dev = 160
num_test = 200

X_train, y_train = X[:num_train], y[:num_train]
X_dev, y_dev = X[num_train:num_train + num_dev], y[num_train:num_train + num_dev]
X_test, y_test = X[num_train + num_dev:], y[num_train + num_dev:]

y_train = y_train.reshape([-1,1])
y_dev = y_dev.reshape([-1,1])
y_test = y_test.reshape([-1,1])

2、模型构建

2.1线性层算子

from nndl.op import Op
import torch
import numpy as np
# 实现线性层算子
class Linear(Op):
    def __init__(self, input_size, output_size, name, weight_init=np.random.standard_normal, bias_init=torch.zeros):

        self.params = {}
        # 初始化权重
        self.params['W'] = weight_init([input_size, output_size])
        self.params['W'] = torch.as_tensor(self.params['W'],dtype=torch.float32)
        # 初始化偏置
        self.params['b'] = bias_init([1, output_size])
        self.inputs = None

        self.name = name

    def forward(self, inputs):
        self.inputs = inputs

        outputs = torch.matmul(self.inputs, self.params['W']) + self.params['b']
        return outputs

2.2Logistic层算子

class Logistic(Op):
    def __init__(self):
        self.inputs = None
        self.outputs = None

    def forward(self, inputs):

        outputs = 1.0 / (1.0 + torch.exp(-inputs))
        self.outputs = outputs
        return outputs

2.3层的串行组合

# 实现一个两层前馈神经网络
class Model_MLP_L2(Op):
    def __init__(self, input_size, hidden_size, output_size):
        self.fc1 = Linear(input_size, hidden_size, name="fc1")
        self.act_fn1 = Logistic()
        self.fc2 = Linear(hidden_size, output_size, name="fc2")
        self.act_fn2 = Logistic()

    def __call__(self, X):
        return self.forward(X)

    def forward(self, X):
        z1 = self.fc1(X)
        a1 = self.act_fn1(z1)
        z2 = self.fc2(a1)
        a2 = self.act_fn2(z2)
        return a2

测试一下

# 实例化模型
model = Model_MLP_L2(input_size=5, hidden_size=10, output_size=1)
# 随机生成1条长度为5的数据
X = torch.rand([1, 5])
result = model(X)
print ("result: ", result)

3、损失函数

# 实现交叉熵损失函数
class BinaryCrossEntropyLoss(Op):
    def __init__(self):
        self.predicts = None
        self.labels = None
        self.num = None

    def __call__(self, predicts, labels):
        return self.forward(predicts, labels)

    def forward(self, predicts, labels):
        self.predicts = predicts
        self.labels = labels
        self.num = self.predicts.shape[0]
        loss = -1. / self.num * (torch.matmul(self.labels.t(), torch.log(self.predicts)) + torch.matmul((1-self.labels.t()), torch.log(1-self.predicts)))
        loss = torch.squeeze(loss, 1)
        return loss

4、模型优化

反向传播

损失函数


# 实现交叉熵损失函数
class BinaryCrossEntropyLoss(Op):
    def __init__(self, model):
        self.predicts = None
        self.labels = None
        self.num = None

        self.model = model

    def __call__(self, predicts, labels):
        return self.forward(predicts, labels)

    def forward(self, predicts, labels):

        self.predicts = predicts
        self.labels = labels
        self.num = self.predicts.shape[0]
        loss = -1. / self.num * (torch.matmul(self.labels.t(), torch.log(self.predicts))
                                 + torch.matmul((1 - self.labels.t()), torch.log(1 - self.predicts)))

        loss = torch.squeeze(loss, axis=1)
        return loss

    def backward(self):
        # 计算损失函数对模型预测的导数
        loss_grad_predicts = -1.0 * (self.labels / self.predicts -
                                     (1 - self.labels) / (1 - self.predicts)) / self.num

        # 梯度反向传播
        self.model.backward(loss_grad_predicts)

 Logistic算子

class Logistic(Op):
    def __init__(self):
        self.inputs = None
        self.outputs = None
        self.params = None

    def forward(self, inputs):
        outputs = 1.0 / (1.0 + torch.exp(-inputs))
        self.outputs = outputs
        return outputs

    def backward(self, grads):
        # 计算Logistic激活函数对输入的导数
        outputs_grad_inputs = torch.multiply(self.outputs, (1.0 - self.outputs))
        return torch.multiply(grads,outputs_grad_inputs)

 线性层

class Linear(Op):
    def __init__(self, input_size, output_size, name, weight_init=np.random.standard_normal, bias_init=torch.zeros):
        self.params = {}
        self.params['W'] = weight_init([input_size, output_size])
        self.params['W'] = torch.as_tensor(self.params['W'],dtype=torch.float32)
        self.params['b'] = bias_init([1, output_size])

        self.inputs = None
        self.grads = {}

        self.name = name

    def forward(self, inputs):
        self.inputs = inputs
        outputs = torch.matmul(self.inputs, self.params['W']) + self.params['b']
        return outputs

    def backward(self, grads):
        self.grads['W'] = torch.matmul(self.inputs.T, grads)
        self.grads['b'] = torch.sum(grads, dim=0)

        # 线性层输入的梯度
        return torch.matmul(grads, self.params['W'].T)

 整个网络

class Model_MLP_L2(Op):
    def __init__(self, input_size, hidden_size, output_size):
        # 线性层
        self.fc1 = Linear(input_size, hidden_size, name="fc1")
        # Logistic激活函数层
        self.act_fn1 = Logistic()
        self.fc2 = Linear(hidden_size, output_size, name="fc2")
        self.act_fn2 = Logistic()

        self.layers = [self.fc1, self.act_fn1, self.fc2, self.act_fn2]

    def __call__(self, X):
        return self.forward(X)

    # 前向计算
    def forward(self, X):
        z1 = self.fc1(X)
        a1 = self.act_fn1(z1)
        z2 = self.fc2(a1)
        a2 = self.act_fn2(z2)
        return a2

    # 反向计算
    def backward(self, loss_grad_a2):
        loss_grad_z2 = self.act_fn2.backward(loss_grad_a2)
        loss_grad_a1 = self.fc2.backward(loss_grad_z2)
        loss_grad_z1 = self.act_fn1.backward(loss_grad_a1)
        loss_grad_inputs = self.fc1.backward(loss_grad_z1)

优化器

from nndl.opitimizer import Optimizer

class BatchGD(Optimizer):
    def __init__(self, init_lr, model):
        super(BatchGD, self).__init__(init_lr=init_lr, model=model)

    def step(self):
        # 参数更新
        for layer in self.model.layers: # 遍历所有层
            if isinstance(layer.params, dict):
                for key in layer.params.keys():
                    layer.params[key] = layer.params[key] - self.init_lr * layer.grads[key]

5、完善Runner类：RunnerV2_1

import os
class RunnerV2_1(object):
    def __init__(self, model, optimizer, metric, loss_fn, **kwargs):
        self.model = model
        self.optimizer = optimizer
        self.loss_fn = loss_fn
        self.metric = metric

        # 记录训练过程中的评估指标变化情况
        self.train_scores = []
        self.dev_scores = []

        # 记录训练过程中的评价指标变化情况
        self.train_loss = []
        self.dev_loss = []

    def train(self, train_set, dev_set, **kwargs):
        # 传入训练轮数，如果没有传入值则默认为0
        num_epochs = kwargs.get("num_epochs", 0)
        # 传入log打印频率，如果没有传入值则默认为100
        log_epochs = kwargs.get("log_epochs", 100)

        # 传入模型保存路径
        save_dir = kwargs.get("save_dir", None)

        # 记录全局最优指标
        best_score = 0
        # 进行num_epochs轮训练
        for epoch in range(num_epochs):
            X, y = train_set
            # 获取模型预测
            logits = self.model(X)
            # 计算交叉熵损失
            trn_loss = self.loss_fn(logits, y)  # return a tensor

            self.train_loss.append(trn_loss.item())
            # 计算评估指标
            trn_score = self.metric(logits, y).item()
            self.train_scores.append(trn_score)

            self.loss_fn.backward()

            # 参数更新
            self.optimizer.step()

            dev_score, dev_loss = self.evaluate(dev_set)
            # 如果当前指标为最优指标，保存该模型
            if dev_score > best_score:
                print(f"[Evaluate] best accuracy performence has been updated: {best_score:.5f} --> {dev_score:.5f}")
                best_score = dev_score
                if save_dir:
                    self.save_model(save_dir)

            if log_epochs and epoch % log_epochs == 0:
                print(f"[Train] epoch: {epoch}/{num_epochs}, loss: {trn_loss.item()}")

    def evaluate(self, data_set):
        X, y = data_set
        # 计算模型输出
        logits = self.model(X)
        # 计算损失函数
        loss = self.loss_fn(logits, y).item()
        self.dev_loss.append(loss)
        # 计算评估指标
        score = self.metric(logits, y).item()
        self.dev_scores.append(score)
        return score, loss

    def predict(self, X):
        return self.model(X)

    def save_model(self, save_dir):
        # 对模型每层参数分别进行保存，保存文件名称与该层名称相同
        for layer in self.model.layers:  # 遍历所有层
            if isinstance(layer.params, dict):
               torch.save(layer.params, os.path.join(save_dir, layer.name+".pdparams"))

    def load_model(self, model_dir):
        # 获取所有层参数名称和保存路径之间的对应关系
        model_file_names = os.listdir(model_dir)
        name_file_dict = {}
        for file_name in model_file_names:
            name = file_name.replace(".pdparams", "")
            name_file_dict[name] = os.path.join(model_dir, file_name)

        # 加载每层参数
        for layer in self.model.layers:  # 遍历所有层
            if isinstance(layer.params, dict):
                name = layer.name
                file_path = name_file_dict[name]
                layer.params = torch.load(file_path, weights_only=True)

6、模型训练

from nndl.metric import accuracy
epoch_num = 1000

model_saved_dir = 'G:\大三上学期\深度学习\实验6'

# 输入层维度为2
input_size = 2
# 隐藏层维度为5
hidden_size = 4
# 输出层维度为1
output_size = 1

# 定义网络
model = Model_MLP_L2(input_size=input_size, hidden_size=hidden_size, output_size=output_size)

# 损失函数
loss_fn = BinaryCrossEntropyLoss(model)

# 优化器
learning_rate = 0.1
optimizer = BatchGD(learning_rate, model)

# 评价方法
metric = accuracy

# 实例化RunnerV2_1类，并传入训练配置
runner = RunnerV2_1(model, optimizer, metric, loss_fn)

runner.train([X_train, y_train], [X_dev, y_dev], num_epochs=epoch_num, log_epochs=50, save_dir=model_saved_dir)

运行结果 

[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250
[Evaluate] best accuracy performence has been updated: 0.81250 --> 0.81875
[Evaluate] best accuracy performence has been updated: 0.81875 --> 0.83125
[Evaluate] best accuracy performence has been updated: 0.83125 --> 0.84375
[Evaluate] best accuracy performence has been updated: 0.84375 --> 0.85000
[Evaluate] best accuracy performence has been updated: 0.85000 --> 0.85625
[Evaluate] best accuracy performence has been updated: 0.85625 --> 0.86250
[Train] epoch: 50/1000, loss: 0.582136332988739
[Evaluate] best accuracy performence has been updated: 0.86250 --> 0.86875[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250
[Evaluate] best accuracy performence has been updated: 0.81250 --> 0.81875
[Evaluate] best accuracy performence has been updated: 0.81875 --> 0.83125
[Evaluate] best accuracy performence has been updated: 0.83125 --> 0.84375
[Evaluate] best accuracy performence has been updated: 0.84375 --> 0.85000
[Evaluate] best accuracy performence has been updated: 0.85000 --> 0.85625
[Evaluate] best accuracy performence has been updated: 0.85625 --> 0.86250
[Train] epoch: 50/1000, loss: 0.582136332988739
[Evaluate] best accuracy performence has been updated: 0.86250 --> 0.86875
[Evaluate] best accuracy performence has been updated: 0.86875 --> 0.87500
[Train] epoch: 100/1000, loss: 0.5028225779533386
[Train] epoch: 150/1000, loss: 0.4436149597167969[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250
[Evaluate] best accuracy performence has been updated: 0.81250 --> 0.81875
[Evaluate] best accuracy performence has been updated: 0.81875 --> 0.83125
[Evaluate] best accuracy performence has been updated: 0.83125 --> 0.84375
[Evaluate] best accuracy performence has been updated: 0.84375 --> 0.85000
[Evaluate] best accuracy performence has been updated: 0.85000 --> 0.85625
[Evaluate] best accuracy performence has been updated: 0.85625 --> 0.86250
[Train] epoch: 50/1000, loss: 0.582136332988739
[Evaluate] best accuracy performence has been updated: 0.86250 --> 0.86875
[Evaluate] best accuracy performence has been updated: 0.86875 --> 0.87500
[Train] epoch: 100/1000, loss: 0.5028225779533386
[Train] epoch: 150/1000, loss: 0.4436149597167969
[Train] epoch: 200/1000, loss: 0.399962842464447[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250
[Evaluate] best accuracy performence has been updated: 0.81250 --> 0.81875
[Evaluate] best accuracy performence has been updated: 0.81875 --> 0.83125
[Evaluate] best accuracy performence has been updated: 0.83125 --> 0.84375
[Evaluate] best accuracy performence has been updated: 0.84375 --> 0.85000
[Evaluate] best accuracy performence has been updated: 0.85000 --> 0.85625
[Evaluate] best accuracy performence has been updated: 0.85625 --> 0.86250
[Train] epoch: 50/1000, loss: 0.582136332988739
[Evaluate] best accuracy performence has been updated: 0.86250 --> 0.86875
[Evaluate] best accuracy performence has been updated: 0.86875 --> 0.87500
[Train] epoch: 100/1000, loss: 0.5028225779533386
[Train] epoch: 150/1000, loss: 0.4436149597167969
[Train] epoch: 200/1000, loss: 0.399962842464447
[Evaluate] best accuracy performence has been updated: 0.87500 --> 0.88125[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250
[Evaluate] best accuracy performence has been updated: 0.81250 --> 0.81875
[Evaluate] best accuracy performence has been updated: 0.81875 --> 0.83125
[Evaluate] best accuracy performence has been updated: 0.83125 --> 0.84375
[Evaluate] best accuracy performence has been updated: 0.84375 --> 0.85000
[Evaluate] best accuracy performence has been updated: 0.85000 --> 0.85625
[Evaluate] best accuracy performence has been updated: 0.85625 --> 0.86250
[Train] epoch: 50/1000, loss: 0.582136332988739
[Evaluate] best accuracy performence has been updated: 0.86250 --> 0.86875
[Evaluate] best accuracy performence has been updated: 0.86875 --> 0.87500
[Train] epoch: 100/1000, loss: 0.5028225779533386
[Train] epoch: 150/1000, loss: 0.4436149597167969
[Train] epoch: 200/1000, loss: 0.399962842464447
[Evaluate] best accuracy performence has been updated: 0.87500 --> 0.88125
[Train] epoch: 250/1000, loss: 0.36777132749557495
[Train] epoch: 300/1000, loss: 0.3435978889465332
[Evaluate] best accuracy performence has been updated: 0.88125 --> 0.88750
[Train] epoch: 350/1000, loss: 0.32495132088661194[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250
[Evaluate] best accuracy performence has been updated: 0.81250 --> 0.81875
[Evaluate] best accuracy performence has been updated: 0.81875 --> 0.83125
[Evaluate] best accuracy performence has been updated: 0.83125 --> 0.84375
[Evaluate] best accuracy performence has been updated: 0.84375 --> 0.85000
[Evaluate] best accuracy performence has been updated: 0.85000 --> 0.85625
[Evaluate] best accuracy performence has been updated: 0.85625 --> 0.86250
[Train] epoch: 50/1000, loss: 0.582136332988739
[Evaluate] best accuracy performence has been updated: 0.86250 --> 0.86875
[Evaluate] best accuracy performence has been updated: 0.86875 --> 0.87500
[Train] epoch: 100/1000, loss: 0.5028225779533386
[Train] epoch: 150/1000, loss: 0.4436149597167969
[Train] epoch: 200/1000, loss: 0.399962842464447
[Evaluate] best accuracy performence has been updated: 0.87500 --> 0.88125
[Train] epoch: 250/1000, loss: 0.36777132749557495
[Train] epoch: 300/1000, loss: 0.3435978889465332
[Evaluate] best accuracy performence has been updated: 0.88125 --> 0.88750
[Train] epoch: 350/1000, loss: 0.32495132088661194
[Train] epoch: 400/1000, loss: 0.31017178297042847[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250
[Evaluate] best accuracy performence has been updated: 0.81250 --> 0.81875
[Evaluate] best accuracy performence has been updated: 0.81875 --> 0.83125
[Evaluate] best accuracy performence has been updated: 0.83125 --> 0.84375
[Evaluate] best accuracy performence has been updated: 0.84375 --> 0.85000
[Evaluate] best accuracy performence has been updated: 0.85000 --> 0.85625
[Evaluate] best accuracy performence has been updated: 0.85625 --> 0.86250
[Train] epoch: 50/1000, loss: 0.582136332988739
[Evaluate] best accuracy performence has been updated: 0.86250 --> 0.86875
[Evaluate] best accuracy performence has been updated: 0.86875 --> 0.87500
[Train] epoch: 100/1000, loss: 0.5028225779533386
[Train] epoch: 150/1000, loss: 0.4436149597167969
[Train] epoch: 200/1000, loss: 0.399962842464447
[Evaluate] best accuracy performence has been updated: 0.87500 --> 0.88125
[Train] epoch: 250/1000, loss: 0.36777132749557495
[Train] epoch: 300/1000, loss: 0.3435978889465332
[Evaluate] best accuracy performence has been updated: 0.88125 --> 0.88750
[Train] epoch: 350/1000, loss: 0.32495132088661194
[Train] epoch: 400/1000, loss: 0.31017178297042847
[Evaluate] best accuracy performence has been updated: 0.88750 --> 0.89375
[Train] epoch: 450/1000, loss: 0.2981906533241272
[Train] epoch: 500/1000, loss: 0.28831884264945984
[Train] epoch: 550/1000, loss: 0.28009912371635437[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250
[Evaluate] best accuracy performence has been updated: 0.81250 --> 0.81875
[Evaluate] best accuracy performence has been updated: 0.81875 --> 0.83125
[Evaluate] best accuracy performence has been updated: 0.83125 --> 0.84375
[Evaluate] best accuracy performence has been updated: 0.84375 --> 0.85000
[Evaluate] best accuracy performence has been updated: 0.85000 --> 0.85625
[Evaluate] best accuracy performence has been updated: 0.85625 --> 0.86250
[Train] epoch: 50/1000, loss: 0.582136332988739
[Evaluate] best accuracy performence has been updated: 0.86250 --> 0.86875
[Evaluate] best accuracy performence has been updated: 0.86875 --> 0.87500
[Train] epoch: 100/1000, loss: 0.5028225779533386
[Train] epoch: 150/1000, loss: 0.4436149597167969
[Train] epoch: 200/1000, loss: 0.399962842464447
[Evaluate] best accuracy performence has been updated: 0.87500 --> 0.88125
[Train] epoch: 250/1000, loss: 0.36777132749557495
[Train] epoch: 300/1000, loss: 0.3435978889465332
[Evaluate] best accuracy performence has been updated: 0.88125 --> 0.88750
[Train] epoch: 350/1000, loss: 0.32495132088661194
[Train] epoch: 400/1000, loss: 0.31017178297042847
[Evaluate] best accuracy performence has been updated: 0.88750 --> 0.89375
[Train] epoch: 450/1000, loss: 0.2981906533241272
[Train] epoch: 500/1000, loss: 0.28831884264945984
[Train] epoch: 550/1000, loss: 0.28009912371635437
[Train] epoch: 600/1000, loss: 0.27321189641952515[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250
[Evaluate] best accuracy performence has been updated: 0.81250 --> 0.81875
[Evaluate] best accuracy performence has been updated: 0.81875 --> 0.83125
[Evaluate] best accuracy performence has been updated: 0.83125 --> 0.84375
[Evaluate] best accuracy performence has been updated: 0.84375 --> 0.85000
[Evaluate] best accuracy performence has been updated: 0.85000 --> 0.85625
[Evaluate] best accuracy performence has been updated: 0.85625 --> 0.86250
[Train] epoch: 50/1000, loss: 0.582136332988739
[Evaluate] best accuracy performence has been updated: 0.86250 --> 0.86875
[Evaluate] best accuracy performence has been updated: 0.86875 --> 0.87500
[Train] epoch: 100/1000, loss: 0.5028225779533386
[Train] epoch: 150/1000, loss: 0.4436149597167969
[Train] epoch: 200/1000, loss: 0.399962842464447
[Evaluate] best accuracy performence has been updated: 0.87500 --> 0.88125
[Train] epoch: 250/1000, loss: 0.36777132749557495
[Train] epoch: 300/1000, loss: 0.3435978889465332
[Evaluate] best accuracy performence has been updated: 0.88125 --> 0.88750
[Train] epoch: 350/1000, loss: 0.32495132088661194
[Train] epoch: 400/1000, loss: 0.31017178297042847
[Evaluate] best accuracy performence has been updated: 0.88750 --> 0.89375
[Train] epoch: 450/1000, loss: 0.2981906533241272
[Train] epoch: 500/1000, loss: 0.28831884264945984
[Train] epoch: 550/1000, loss: 0.28009912371635437
[Train] epoch: 600/1000, loss: 0.27321189641952515
[Train] epoch: 650/1000, loss: 0.2674194276332855
[Train] epoch: 700/1000, loss: 0.26253607869148254
[Train] epoch: 750/1000, loss: 0.25841012597084045[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.50000
[Train] epoch: 0/1000, loss: 0.7069255709648132
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.50625
[Evaluate] best accuracy performence has been updated: 0.50625 --> 0.53750
[Evaluate] best accuracy performence has been updated: 0.53750 --> 0.55625
[Evaluate] best accuracy performence has been updated: 0.55625 --> 0.58750
[Evaluate] best accuracy performence has been updated: 0.58750 --> 0.60000
[Evaluate] best accuracy performence has been updated: 0.60000 --> 0.61875
[Evaluate] best accuracy performence has been updated: 0.61875 --> 0.62500
[Evaluate] best accuracy performence has been updated: 0.62500 --> 0.64375
[Evaluate] best accuracy performence has been updated: 0.64375 --> 0.67500
[Evaluate] best accuracy performence has been updated: 0.67500 --> 0.70000
[Evaluate] best accuracy performence has been updated: 0.70000 --> 0.71250
[Evaluate] best accuracy performence has been updated: 0.71250 --> 0.74375
[Evaluate] best accuracy performence has been updated: 0.74375 --> 0.75625
[Evaluate] best accuracy performence has been updated: 0.75625 --> 0.76875
[Evaluate] best accuracy performence has been updated: 0.76875 --> 0.77500
[Evaluate] best accuracy performence has been updated: 0.77500 --> 0.78750
[Evaluate] best accuracy performence has been updated: 0.78750 --> 0.79375
[Evaluate] best accuracy performence has been updated: 0.79375 --> 0.80000
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.81250
[Evaluate] best accuracy performence has been updated: 0.81250 --> 0.81875
[Evaluate] best accuracy performence has been updated: 0.81875 --> 0.83125
[Evaluate] best accuracy performence has been updated: 0.83125 --> 0.84375
[Evaluate] best accuracy performence has been updated: 0.84375 --> 0.85000
[Evaluate] best accuracy performence has been updated: 0.85000 --> 0.85625
[Evaluate] best accuracy performence has been updated: 0.85625 --> 0.86250
[Train] epoch: 50/1000, loss: 0.582136332988739
[Evaluate] best accuracy performence has been updated: 0.86250 --> 0.86875
[Evaluate] best accuracy performence has been updated: 0.86875 --> 0.87500
[Train] epoch: 100/1000, loss: 0.5028225779533386
[Train] epoch: 150/1000, loss: 0.4436149597167969
[Train] epoch: 200/1000, loss: 0.399962842464447
[Evaluate] best accuracy performence has been updated: 0.87500 --> 0.88125
[Train] epoch: 250/1000, loss: 0.36777132749557495
[Train] epoch: 300/1000, loss: 0.3435978889465332
[Evaluate] best accuracy performence has been updated: 0.88125 --> 0.88750
[Train] epoch: 350/1000, loss: 0.32495132088661194
[Train] epoch: 400/1000, loss: 0.31017178297042847
[Evaluate] best accuracy performence has been updated: 0.88750 --> 0.89375
[Train] epoch: 450/1000, loss: 0.2981906533241272
[Train] epoch: 500/1000, loss: 0.28831884264945984
[Train] epoch: 550/1000, loss: 0.28009912371635437
[Train] epoch: 600/1000, loss: 0.27321189641952515
[Train] epoch: 650/1000, loss: 0.2674194276332855
[Train] epoch: 700/1000, loss: 0.26253607869148254
[Train] epoch: 750/1000, loss: 0.25841012597084045
[Train] epoch: 800/1000, loss: 0.25491634011268616
[Train] epoch: 850/1000, loss: 0.2519505023956299
[Train] epoch: 900/1000, loss: 0.24942593276500702
[Train] epoch: 950/1000, loss: 0.24727044999599457

可视化观察训练集与验证集的损失函数变化情况。

import matplotlib.pyplot as plt
# 打印训练集和验证集的损失
plt.figure()
plt.plot(range(epoch_num), runner.train_loss, color="#8E004D", label="Train loss")
plt.plot(range(epoch_num), runner.dev_loss, color="#E20079", linestyle='--', label="Dev loss")
plt.xlabel("epoch", fontsize='x-large')
plt.ylabel("loss", fontsize='x-large')
plt.legend(fontsize='large')
plt.savefig('fw-loss2.pdf')
plt.show()

7、性能评价

# 加载训练好的模型
runner.load_model(model_saved_dir)
# 在测试集上对模型进行评价
score, loss = runner.evaluate([X_test, y_test])

print("[Test] score/loss: {:.4f}/{:.4f}".format(score, loss))

import math

# 均匀生成40000个数据点
x1, x2 = torch.meshgrid(torch.linspace(-math.pi, math.pi, 200), torch.linspace(-math.pi, math.pi, 200), indexing='ij')

x = torch.stack([torch.flatten(x1), torch.flatten(x2)], 1)

# 预测对应类别
y = runner.predict(x)
# y = torch.squeeze(torch.as_tensor(torch.can_cast((y>=0.5).dtype,torch.float32)))

# 绘制类别区域
plt.ylabel('x2')
plt.xlabel('x1')
plt.scatter(x[:,0].tolist(), x[:,1].tolist(), c=y.tolist(), cmap=plt.cm.Spectral)

plt.scatter(X_train[:, 0].tolist(), X_train[:, 1].tolist(), marker='*', c=torch.squeeze(y_train,-1).tolist())
plt.scatter(X_dev[:, 0].tolist(), X_dev[:, 1].tolist(), marker='*', c=torch.squeeze(y_dev,-1).tolist())
plt.scatter(X_test[:, 0].tolist(), X_test[:, 1].tolist(), marker='*', c=torch.squeeze(y_test,-1).tolist())

plt.show()

HBU深度学习实验8-前馈神经网络（4）
ckh20040422的博客
11-03 662
实现一个神经网络前，需要先初始化模型参数。如果对每一层的权重和偏置都用0初始化，那么通过第一遍前向计算，所有隐藏层神经元的激活值都相同；在反向传播时，所有权重的更新也都相同，这样会导致隐藏层神经元没有差异性，出现。看上面的权重都一样从输出结果看，二分类准确率为50%左右，说明模型没有学到任何内容。训练和验证loss几乎没有怎么下降。为了避免对称权重现象，可以使用高斯分布或均匀分布初始化神经网络的参数。
HBU深度学习实验7-前馈神经网络（3）
ckh20040422的博客
10-24 662
import os# 新增make_moons函数1X = X[idx]y = y[idx]# 判断是二分类任务还是多分类任务，preds.shape[1]=1时为二分类任务，preds.shape[1]>1时为多分类任务else:# 绘制坐标轴和图例# 绘制坐标轴和图例plt.show()# 使用'torch.nn.functional.sigmoid'定义 Logistic 激活函数# 前向计算return a2# 记录训练过程中的评估指标变化情况。
HBU深度学习实验5-前馈神经网络（1）
ckh20040422的博客
10-12 334
什么是活性值？神经网络中每个神经元在接收输入后计算得到的输出值。什么是净活性值？在激活函数应用之前，神经元接收到的加权输入的总和，净活性值在经过激活函数后，会得到活性值。
HBU深度学习实验9-前馈神经网络（5）
ckh20040422的博客
11-03 668
随机梯度下降收敛速度快，但是波动较大，在最优解处出现波动很难判断其是否收敛到一个合理的值。因为批梯度下降所需要的时间空间成本大，我们考虑随机抽取一个样本来获取梯度，更新参数 θ。：训练速度快，每次迭代只需要一个样本，相对于批梯度下降，总时间、空间开销小。：考虑到了全局数据，更新稳定，震荡小，每次更新都会朝着正确的方向。将数据集分为m /n个集合，如果有余，将剩余样本单独作为一个集合。：噪声大导致高方差。根据整个数据集求取损失函数的梯度，来更新参数θ的值。根据上图可以看到，批梯度下降收敛稳定，震荡小。
HBU深度学习实验14-循环神经网络（1）
ckh20040422的博客
12-04 1209
循环神经网络（Recurrent Neural Network，RNN）是一类具有短期记忆能力的神经网络．在循环神经网络中，神经元不但可以接受其他神经元的信息，也可以接受自身的信息，形成具有环路的网络结构．和前馈神经网络相比，循环神经网络更加符合生物神经网络的结构．目前，循环神经网络已经被广泛应用在语音识别、语言模型以及自然语言生成等任务上．循环神经网络非常擅于处理序列数据，通过使用带自反馈的神经元，能够处理任意长度的序列数据．给定输入序列，循环神经网络从左到右扫描该序列，并不断调用一个相同的组合函数。
HBU_神经网络与深度学习 作业4 前馈神经网络
m0_61227501的博客
10-09 753
本文为HBU_神经网络与深度学习 作业4的相关内容
HBU_神经网络与深度学习 实验6 前馈神经网络：自动梯度计算 及 优化问题
m0_61227501的博客
10-07 570
本文为HBU_神经网络与深度学习 实验6的实验报告
HBU-NNDL 实验五 前馈神经网络（1）二分类任务
m0_57215376的博客
09-28 897
HBU-nndl 实验五（1）
HBU_神经网络与深度学习 实验5 前馈神经网络：二分类任务
m0_61227501的博客
09-30 656
本文为HBU_神经网络与深度学习 实验5的实验报告
LSTM三个门控机制详解
感谢所有乐于奉献的人，在此不一一具名
05-26 675
LSTM三个门控机制详解
深度学习篇---OC-SORT实际应用效果
道阻且长，行则将至。
05-30 868
OC-SORT算法在准确性、鲁棒性和效率上显著优于SORT、DeepSORT等传统多目标跟踪算法。其以观测为中心的恢复机制（ORU）和在线平滑策略（OOS）有效降低遮挡场景的ID切换率（如MOT17数据集ID切换次数比DeepSORT减少38%），并通过运动方向一致性提升复杂运动匹配精度（MOT20场景MOTA达65.8%）。算法对低质量检测框容错性强（IDF1提升7.2%），且无需场景适配即可泛化至交通、安防等领域。计算效率方面，纯运动模式下可达85FPS（CPU），内存占用减少40%。
深度学习核心网络架构详解（续）：从 Transformers 到生成模型
yzx991013的博客
05-29 863
本文深入探讨了四种重要的深度学习架构：Transformer、生成对抗网络(GAN)、自编码器和强化学习。详细解析了Transformer的自注意力机制及其机器翻译应用，演示了GAN生成手写数字的实现，介绍了自编码器的图像压缩原理，并通过DQN算法解决了CartPole平衡问题。每种架构均包含理论讲解和PyTorch代码实现，展示了它们在不同领域的应用潜力。这些技术代表了深度学习的前沿方向，掌握它们对理解现代AI系统至关重要，也为后续学习更先进的模型奠定了坚实基础。
深度学习教学目录
FJN110的博客
05-30 364
深度学习课程：面向计算机视觉、深度学习小白，本产品包含但不限于以下文档 一、环境配置详解，全平台支持 提供Windows、Linux、树莓派、瑞芯微板（RK）等多平台下的PyTorch与TensorFlow环境配置教程，图文并茂，细致入微，确保每一位学习者都能顺利完成环境搭建。 同时，文档中还详细讲解了服务器部署、AI大模型运行、Docker容器配置、VNC远程连接等高级内容，适用于科研和生产环境。
【专题】深度学习期末复习资料（题库）
Pqf18064375973的博客
05-30 262
深度学习期末复习资料（题库）
正则化-深度学习
FJN110的博客
05-30 19
正则化参数（通常记作 λ\lambdaλ 或 α\alphaα）在机器学习中的作用是通过控制模型的复杂度来防止过拟合。
DAY 40 训练和测试的规范写法
最新发布
MasterLLL0228的博客
05-30 173
仔细学习下测试和训练代码的逻辑，这是基础，这个代码框架后续会一直沿用，后续的重点慢慢就是转向模型定义阶段了。dropout操作：训练阶段随机丢弃神经元，测试阶段eval模式关闭dropout。展平操作：除第一个维度batchsize外全部展平。彩色和灰度图片测试和训练的规范写法：封装在函数中。
基于多尺度卷积和扩张卷积-LSTM的多变量时间序列预测
专注AI大模型,软件混淆,授权
05-29 71
本文提出了一种结合多尺度卷积、扩张卷积和LSTM的混合神经网络模型，用于多变量时间序列预测。该模型通过多尺度卷积捕获不同时间尺度的局部特征，利用扩张卷积扩大感受野捕捉长期依赖，并借助LSTM处理序列数据的时序关系。文章详细介绍了模型架构、关键技术原理，并提供了完整的PyTorch实现代码，包括数据预处理、模型定义、训练过程和评估方法。实验结果表明，该模型能有效提取时空特征，在金融、气象、交通等领域具有广泛应用前景。代码实现完整且注释详尽，便于读者理解和使用。
【深度学习-pytorch篇】3. 优化器实现：momentum,NAG,AdaGrad,RMSProp,Adam
weixin_48846514的博客
05-28 1151
优化器实现：momentum,NAG,AdaGrad,RMSProp,Adam
深度学习实战110-基于深度学习的工业系统故障诊断技术研究（卷积网络+注意力机制模型）
微学AI的博客
05-30 123
工业系统故障诊断是确保现代工业设备安全稳定运行的关键技术环节。随着工业自动化和智能化水平的不断提高，传统故障诊断方法在应对日益复杂、多变的工业环境时显得力不从心。基于深度学习的故障诊断技术因其强大的特征学习能力和自适应性，已成为当前研究的热点和工业应用的前沿。本文将探讨一种融合卷积神经网络(CNN)和注意力机制的深度学习模型，用于工业系统故障诊断，包括项目背景、系统架构、技术原理、数据样例以及相关代码实现。
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值