tensorflow实现花分类-526互联

1. 花数据集

　　数据集来自kaggle官网下载。分为五类花，每类花有1000张图片。下载方式可以参考我的https://www.cnblogs.com/wancy/p/17446715.html

2. 图片大小分布图

　　训练模型之前，我们会需要先分析数据集，由于此类数据集每类花的图片数量一样，是均衡的。训练模型之前，我们需要传入合适图片大小输入，选择合适的图片大小也会对模型最终性能有一定影响。所以训练模型之前先观察图片大小分布。

import os
import cv2
import numpy as np
import matplotlib.pyplot as plt

# 读取图片文件夹中所有图片的大小信息
def get_image_sizes(image_folder):
   sizes = []
   for folder_name in os.listdir(image_folder):
       # print("文件夹名"+folder_name)
       folder_path = os.path.join(image_folder, folder_name)
       # print(folder_path)
       if os.path.isdir(folder_path):
           for img_name in os.listdir(folder_path):
               image = cv2.imread(folder_path+"/"+img_name)
               sizes.append((image.shape[0], image.shape[1]))  # (height, width)
   return sizes

# 绘制散点图
def plot_size_scatter(sizes):
   x = [size[1] for size in sizes] # width
   y = [size[0] for size in sizes] # height
   plt.scatter(x, y, s=5, alpha=0.5, c='steelblue')
   plt.title('Image Size Scatter')
   plt.xlabel('Width (pixel)')
   plt.ylabel('Height (pixel)')
   plt.show()

# 代码
if __name__ == '__main__':
   sizes = get_image_sizes('./5-flower-types-classification-dataset/flower_images')
   print(f'Total images: {len(sizes)}')
   plot_size_scatter(sizes)

　　可以发现，图片大部分大小范围在(200x200,1000,1000)以内，在此之内选择比较合适。

3. tensorflow训练模型

import tensorflow as tf
import os

from matplotlib import pyplot as plt
#from tensorflow.keras.preprocessing import image
from tensorflow.keras.callbacks import TensorBoard
# 创建TensorBoard回调函数
# tensorboard = TensorBoard(log_dir='./log', historytogram_freq=1)
data_dir = './5-flower-types-classification-dataset/flower_images'  # 数据路径

# 设置图像尺寸和批次大小
img_size = (224, 224)
batch_size = 32

# 将数据文件夹名称存储在列表中
data_folders = os.listdir(data_dir)

# 使用 ImageDataGenerator 类读取和增强数据
train_datagen = image.ImageDataGenerator(rescale=1. / 255,rotation_range=20,zoom_range=0.2,horizontal_flip=True,validation_split=0.2)

# 读取并划分训练集和测试集数据
train_generator = train_datagen.flow_from_directory(data_dir,target_size=img_size,batch_size=batch_size,class_mode='categorical',subset='training')
valid_generator = train_datagen.flow_from_directory(data_dir,target_size=img_size,batch_size=batch_size,class_mode='categorical',subset='validation')


#类别标签字典
class_indices = train_generator.class_indices
print("class_indices",class_indices)####{'Lilly': 0, 'Lotus': 1, 'Orchid': 2, 'Sunflower': 3, 'Tulip': 4}
# 构建模型
# model = tf.keras.Sequential([
#     tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(img_size[0], img_size[1], 3)),
#     tf.keras.layers.MaxPooling2D((2, 2)),
#     tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
#     tf.keras.layers.MaxPooling2D((2, 2)),
#     tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
#     tf.keras.layers.MaxPooling2D((2, 2)),
#     tf.keras.layers.Flatten(),
#     tf.keras.layers.Dense(512, activation='relu'),
#     tf.keras.layers.Dropout(0.5),
#     tf.keras.layers.Dense(len(data_folders), activation='softmax')
# ])
#定义模型
model=tf.keras.Sequential()
#conv_layer = layers.Conv2D(64, (3, 3), bias_initializer="zeros", kernel_initializer=GlorotUniform(seed=42))
model.add(tf.keras.layers.Conv2D(32,(3,3),input_shape=(img_size[0], img_size[1], 3),activation="relu",padding="same"))
model.add(tf.keras.layers.Conv2D(32,(3,3),activation="relu",padding="same"))
#tf.keras.layers.Dropout(0.5)
model.add(tf.keras.layers.MaxPool2D())#默认2*2，步长也为2

model.add(tf.keras.layers.Conv2D(64,(4,4),activation='relu',padding="same"))
model.add(tf.keras.layers.Conv2D(128,(3,3),activation='relu',padding="same"))
model.add(tf.keras.layers.MaxPool2D())#默认2*2，步长也为2
#4维转2维
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(512,activation='relu'))
model.add(tf.keras.layers.Dense(256,activation='relu'))
model.add(tf.keras.layers.Dense(5,activation='softmax'))
#dense_layer = layers.Dense(64, kernel_initializer=GlorotUniform(seed=42))

# 编译和训练模型
# optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
# model.compile(optimizer=optimizer, ...)
"""
在tensorflow.keras中，
如果没有手动指定优化器的学习率，那么model.compile默认使用的Adam优化器的学习率为0.001
"""

#sparse_categorical_crossentropy要求target为非onehot编码，函数内部进行onehot编码实现。categorical_crossentropy要求target为onehot编码。
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
# history = model.fit(train_generator,steps_per_epoch=len(train_generator),epochs=3,validation_data=valid_generator,validation_steps=len(valid_generator),callbacks=[tensorboard])
history = model.fit(train_generator,steps_per_epoch=len(train_generator),epochs=10,shuffle=True,validation_data=valid_generator,validation_steps=len(valid_generator))
#shuffle=True
#每个epoch后，将使用validation_steps个batch的数据进行评估
print(history.history)

# 评估模型并输出结果
test_loss, test_acc = model.evaluate(valid_generator, verbose=2)
print('Test accuracy:', test_acc)
model.save('./model/my_model.h5')
#####################################################################
print(model.summary())
"""
model.summary()是TensorFlow中用于打印模型结构信息的函数。它会输出模型的各层名称、类型、输入和输出张量的形状等信息，以帮助我们了解模型的结构和参数数量。
"""

#画图 性能评估
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss =history.history['loss']
val_loss = history.history['val_loss']

plt.figure(figsize=(15, 5))
plt.subplot(1, 2, 1)
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label='Validation Accuracy')
plt.title('Training and Validation Accuracy')
plt.legend()
#plt.grid()
plt.subplot(1, 2, 2)
plt.plot(loss, label='Training Loss')
plt.plot(val_loss, label='Validation Loss')
plt.title('Training and Validation Loss')
plt.legend()
#plt.grid()
plt.show()