【学习记录】tensorflow图像分类

问题描述

使用tensorflow实现图片分类

数据集

https://www.kaggle.com/datasets/gpiosenka/coffee-bean-dataset-resized-224-x-224、

代码分析

1. 数据集下载解压之后存储在coffee-bean文件夹中，导入数据和可视化图片

import tensorflow as tf
import cv2, pathlib, splitfolders, math, os
from keras.preprocessing.image import ImageDataGenerator
from keras.layers import *
import matplotlib.pyplot as plt
from PIL import Image
import matplotlib.pyplot as plt 
import numpy as np
import PIL 
import tensorflow as tf 
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential


import pathlib
data_dir= pathlib.Path("coffee-bean")

Ant =  list(data_dir.glob("train/Ant/*"))
PIL.Image.open(str(Ant[0]))
Spider = list(data_dir.glob("train/Spider/*"))
PIL.Image.open(str(Spider[0]))

2. 定义图片的宽高，训练集验证集，使用keras.utils.image_dataset_f