train.py代码如下
import torch import torch.nn as nn import torch.optim as optim model_save_path = "my_model.pth" # 定义简单的线性神经网络模型 class MyModel(nn.Module): def __init__(self): super(MyModel, self).__init__() self.output = nn.Linear(2, 4) # 输入2个特征,输出4个类别 def forward(self, x): x = self.output(x) return x def main(): # 数据点 x = torch.tensor([[0, 0], [0, 10], [10, 0], [10, 10]], dtype=torch.float32) y = torch.tensor([0, 1, 2, 3], dtype=torch.long) # 初始化模型 model = MyModel() # 定义损失函数和优化器 criterion = nn.CrossEntropyLoss() optimizer = optim.Adam(model.parameters(), lr=0.01) # 训练模型 num_iterations = 10000 # 迭代次数 for i in range(num_iterations): model.train() # 前向传播:计算预测输出 y_pred = model(x) # 计算损失 loss = criterion(y_pred, y) # 输出每1000次迭代的损失值 if i % 1000 == 0: print(f"迭代 {i},损失:{loss.item():.4f}") # 反向传播与梯度更新 optimizer.zero_grad() # 清除梯度 loss.backward() # 计算梯度 optimizer.step() # 更新参数 # 打印优化后的权重和偏置 print("\n优化后的权重和偏置:") for name, param in model.named_parameters(): if param.requires_grad: print(f"{name} = {param.data.numpy()}") # 保存模型 torch.save(model.state_dict(), model_save_path) print(f"模型已保存到 {model_save_path}") if __name__ == "__main__": main()View Code
运行结果
test.py代码如下
import numpy as np import torch from torch import nn from train import MyModel, model_save_path # 加载模型 loaded_model = MyModel() loaded_model.load_state_dict(torch.load(model_save_path)) loaded_model.eval() # 切换到评估模式 # 定义预测数据 input_data = [0, 9] # 使用加载的模型进行预测 x_new = torch.tensor([input_data], dtype=torch.float32) # 新数据点 y_new_pred = loaded_model(x_new) # 计算预测值 # 使用softmax计算每个类别的概率 softmax = nn.Softmax(dim=1) y_new_pred_probs = softmax(y_new_pred) # 找到预测的类别 predicted_class = torch.argmax(y_new_pred_probs, dim=1) # 将概率分布四舍五入到三位小数 y_new_pred_probs_rounded = np.round(y_new_pred_probs.detach().numpy(), 3) print(f"\n对x = {input_data}的预测类别:{predicted_class.item()}") print(f"预测类别的概率分布:{y_new_pred_probs_rounded}") # 打印权重和偏置 weights = loaded_model.output.weight # 获取输出层权重 bias = loaded_model.output.bias # 获取输出层偏置 print(f"\n模型权重:\n{weights}") print(f"\n模型偏置:\n{bias}") # 计算input_data * 模型权重 + 模型偏置 with torch.no_grad(): linear_output = x_new @ weights.t() + bias print(f"\ninput_data * weights + bias ={linear_output.numpy()}") # 手动计算Softmax概率分布 linear_output_np = linear_output.numpy() exp_output = np.exp(linear_output_np) softmax_output_manual = exp_output / np.sum(exp_output) print(f"\n手动计算的Softmax概率分布:{softmax_output_manual}") print(f"手动计算的预测类别:{np.argmax(softmax_output_manual)}")View Code
运行结果
标签:示例,pred,代码,torch,pytorch,new,print,output,model From: https://www.cnblogs.com/lizhiqiang0204/p/18346540