图像识别-花的分类(tensorflow实现）

本实例使用的数据集是3700张，包含5个种类的花。
flower_photo:daisy(雏菊)/dandelion(蒲公英)/roses(玫瑰）/sunflower（向日葵）/tulips(郁金香)

import matplotlib.pyplot as plt
import numpy as np
import os
import PIL  # Python Imaging Library
import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential

加载数据，并检测数据是否可用。

import pathlib

dataset_url = 'https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz'
# tf.keras.utils.get_file函数的三个参数 文件名，文件路径，是否需要解压缩。
data_dir = tf.keras.utils.get_file('flower_photos', origin=dataset_url, untar=True)
# 创建path对象
data_dir = pathlib.Path(data_dir)

# 检查数据是否可用 ,data_dir.glob获取路径下的所有符合'*/*.jpg'的文件，返回一个generator
image_count = len(list(data_dir.glob('*/*.jpg')))
# print(image_count)

# 检测roses的数据是否正常
roses = list(data_dir.glob('roses/*'))
roses0 = PIL.Image.open(str(roses[0]))
roses1 = PIL.Image.open(str(roses[100]))

daisy = list(data_dir.glob('daisy/*'))
daisy0 = PIL.Image.open(str(daisy[0]))
daisy1 = PIL.Image.open(str(daisy[100]))

dandelion = list(data_dir.glob('dandelion/*'))
dandelion0 = PIL.Image.open(str(dandelion[0]))
dandelion1 = PIL.Image.open(str(dandelion[100]))

对加载器定义一些变量。

batch_size = 32
img_height = 180
img_width = 180

划分训练集和测试集

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=0.2,
    subset='training',
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size
)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=0.2,
    subset='validation',
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size
)

AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

标准化输入数据

normalization_layer = layers.experimental.preprocessing.Rescaling(1. / 255)

normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
image_batch, labels_batch = next(iter(normalized_ds))
first_image = image_batch[0]

创建模型

num_classes = 5
model = Sequential([
    layers.experimental.preprocessing.Rescaling(1. / 255, input_shape=(img_height, img_width, 3)),
    layers.Conv2D(16, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(32, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(64, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Flatten(),
    layers.Dense(128, activation='relu'),
    layers.Dense(num_classes)
])

编译模型

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

训练模型

epochs = 10
history = model.fit(
    train_ds,
    validation_data=val_ds,
    epochs=epochs
)

评估训练的结果，并绘图。

acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(epochs)

plt.figure(figsize=(8,8))
plt.subplot(2,1,1)
plt.plot(epochs_range,acc,label = 'Training Accuracy')
plt.plot(epochs_range,val_acc,label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(2,1,2)
plt.plot(epochs_range,loss,label = 'Training Loss')
plt.plot(epochs_range,val_loss,label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()