数据集

来源网络，经典的猫狗数据集。

引入必要的模块

import tensorflow as tf
from tensorflow import keras
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import glob
import os

获取猫狗图片的路径

train_image_path = glob.glob('d:/datasets/dc/train/*.jpg')

文件名中提取标签（猫为1）

train_image_label = [int(p.split('\')[1][0:3] == 'cat') for p in train_image_path]

 定义函数，读取指定图片文件的数据（数据处理的是RGB格式的图片，不是图片的路径字符串。）。输入路径和标签，返回路径对应文件的文件内容，并解压。jpg是压缩格式的图片，要还原到非压缩的格式。

def load_preprosess_image(path, label):
    image = tf.io.read_file(path)  #读入文件内容
    image = tf.image.decode_jpeg(image, channels=3)  #jpg彩色图片（压缩）解码
    image = tf.image.resize(image, [256, 256])  #大小一致
    image = tf.cast(image, tf.float32)
    image = image/255
    label = tf.reshape(label, [1])
    return image, label

 读入图片数据

train_image_ds = tf.data.Dataset.from_tensor_slices((train_image_path, train_image_label))
AUTOTUNE = tf.data.experimental.AUTOTUNE
train_image_ds = train_image_ds.map(load_preprosess_image, num_parallel_calls=AUTOTUNE)

 构建数据集

BATCH_SIZE = 32
train_count = len(train_image_path)
train_image_ds = train_image_ds.shuffle(train_count).batch(BATCH_SIZE)
train_image_ds = train_image_ds.prefetch(AUTOTUNE)

 处理测试图片集

test_image_path = glob.glob('d:/datasets/dc/test/*.jpg')
test_image_label = [int(p.split('\')[1] == 'cat') for p in test_image_path]
test_image_ds = tf.data.Dataset.from_tensor_slices((test_image_path, test_image_label))
test_image_ds = test_image_ds.map(load_preprosess_image, num_parallel_calls=AUTOTUNE)
test_image_ds = test_image_ds.batch(BATCH_SIZE)
test_image_ds = test_image_ds.prefetch(AUTOTUNE)

 构建模型

model = keras.Sequential([
    tf.keras.layers.Conv2D(64, (3, 3), input_shape=(256, 256, 3), activation='relu'),
    tf.keras.layers.BatchNormalization(),
    tf.keras.layers.Conv2D(256, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(),
    tf.keras.layers.Conv2D(512, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(),
    tf.keras.layers.Conv2D(1024, (3, 3), activation='relu'),
    tf.keras.layers.GlobalAveragePooling2D(),
    tf.keras.layers.Dense(256, activation='relu'),
    tf.keras.layers.Dense(1)
])

  编译模型

model.compile(optimizer="adam",loss="binary_crossentropy",metrics="acc")

 训练

his=model.fit(train_image_ds,epochs=30,
    steps_per_epoch=32,
    validation_data=test_image_ds
)

待完善

最后

以上就是精明楼房为你收集整理的数据分析-神经网络-CNN-猫狗识别案例数据集的全部内容，希望文章能够帮你解决数据分析-神经网络-CNN-猫狗识别案例数据集所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。