ResNet-50 算法实战与解析

- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/kV8ZsJv6cPNzJLEuhPfvXg) 中的学习记录博客**
- **🍖 原作者：[K同学啊](https://mtyjkh.blog.csdn.net/)**

一：理论知识储备

ResNet-50介绍：

ResNet-50有两个基本的块，分别名为Conv Block 和 Identity-Block

二：前期工作

1.设置GPU

import tensorflow as tf
gpus = tf.config.list_physical_devices('GPU')

if gpus:
  tf.config.experimental.set_memory_growth(gpus[0], True)
  tf.config.set_visible_devices(gpus[0], 'GPU')

2.导入数据

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

import os,PIL,pathlib
import numpy as np
from tensorflow import keras
from tensorflow.keras import layers,models

data_dir = "/content/drive/MyDrive/bird_photos"
data_dir = pathlib.Path(dir)

3.查看数据

image_count = len(list(data_dir.glob('*/*')))
print(image_count)

photo_count = {}

for subfolder in data_dir.iterdir():
    if subfolder.is_dir():
        photo_count[subfolder.name] = len(list(subfolder.glob("*.jpg"))) + len(list(subfolder.glob("*.png")))

photo_count

三：数据预处理

1.加载数据

batch_size = 8
img_height =224
img_width =224

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="training",