Day43打卡（补41+42） @浙大疏锦行

DAY 41 简单CNN

知识回顾

1. 数据增强
2. 卷积神经网络定义的写法
3. batch归一化：调整一个批次的分布，常用与图像数据
4. 特征图：只有卷积操作输出的才叫特征图
5. 调度器：直接修改基础学习率

卷积操作常见流程如下：

1. 输入 → 卷积层 → Batch归一化层（可选） → 池化层 → 激活函数 → 下一层

1. Flatten -> Dense (with Dropout，可选) -> Dense (Output)

DAY 42 Grad-CAM与Hook函数

知识点回顾

1. 回调函数
2. lambda函数
3. hook函数的模块钩子和张量钩子
4. Grad-CAM的示例

DAY 43 复习日

import numpy as np
import cv2
import tensorflow as tfdef make_gradcam_heatmap(model, img_array, last_conv_layer_name='conv2d_1'):grad_model = tf.keras.models.Model([model.inputs], [model.get_layer(last_conv_layer_name).output, model.output])with tf.GradientTape() as tape:conv_outputs, predictions = grad_model(img_array)loss = predictions[:, np.argmax(predictions[0])]grads = tape.gradient(loss, conv_outputs)pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))conv_outputs = conv_outputs[0]heatmap = conv_outputs @ pooled_grads[..., tf.newaxis]heatmap = tf.squeeze(heatmap)heatmap = tf.maximum(heatmap, 0) / tf.math.reduce_max(heatmap)return heatmap.numpy()def overlay_heatmap(img, heatmap, alpha=0.4):heatmap = cv2.resize(heatmap, (img.shape[1], img.shape[0]))heatmap = np.uint8(255 * heatmap)heatmap = cv2.applyColorMap(heatmap, cv2.COLORMAP_JET)superimposed_img = heatmap * alpha + imgreturn superimposed_img

@浙大疏锦行