AI算法论文实例及实现

import tensorflow as tf from tensorflow.keras import layers, models def create_lenet5(): model = models.Sequential([ # C1: 卷积层 layers.Conv2D(6, (5, 5), activation='tanh', input_shape=(32, 32, 1), padding='same'), # S2: 平均池化 layers.AveragePooling2D((2, 2), strides=2), # C3: 卷积层 layers.Conv2D(16, (5, 5), activation='tanh'), # S4: 平均池化 layers.AveragePooling2D((2, 2), strides=2), # 展平 layers.Flatten(), # F5: 全连接层 layers.Dense(120, activation='tanh'), # F6: 全连接层 layers.Dense(84, activation='tanh'), # 输出层 layers.Dense(10, activation='softmax') ]) return model # 创建模型 model = create_lenet5() model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) print("LeNet-5模型构建完成")

import torch import torch.nn as nn import torch.nn.functional as F import math class MultiHeadAttention(nn.Module): def __init__(self, d_model, num_heads): super(MultiHeadAttention, self).__init__() assert d_model % num_heads == 0 self.d_model = d_model self.num_heads = num_heads self.d_k = d_model // num_heads self.w_q = nn.Linear(d_model, d_model) self.w_k = nn.Linear(d_model, d_model) self.w_v = nn.Linear(d_model, d_model) self.w_o = nn.Linear(d_model, d_model) def scaled_dot_product_attention(self, q, k, v, mask=None): attn_scores = torch.matmul(q, k.transpose(-2, -1)) / math.sqrt(self.d_k) if mask is not None: attn_scores.masked_fill_(mask == 0, -1e9) attn_weights = F.softmax(attn_scores, dim=-1) output = torch.matmul(attn_weights, v) return output, attn_weights def split_heads(self, x): batch_size, seq_len, d_model = x.size() return x.view(batch_size, seq_len, self.num_heads, self.d_k).transpose(1, 2) def combine_heads(self, x): batch_size, _, seq_len, d_k = x.size() return x.transpose(1, 2).contiguous().view(batch_size, seq_len, self.d_model) def forward(self, q, k, v, mask=None): q = self.split_heads(self.w_q(q)) k = self.split_heads(self.w_k(k)) v = self.split_heads(self.w_v(v)) attn_output, attn_weights = self.scaled_dot_product_attention(q, k, v, mask) output = self.w_o(self.combine_heads(attn_output)) return output, attn_weights # 初始化多头注意力层 attention = MultiHeadAttention(d_model=512, num_heads=8) print("多头注意力机制实现完成")