基于 CNN,搭建一个苹果分类器(二分类)python

好的，我可以为您提供一个基于CNN的苹果分类器的实现，以下是代码：

首先，我们需要导入必要的库：

import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import matplotlib.pyplot as plt

接下来，我们需要准备数据集。我们可以从Kaggle上下载一个包含苹果和非苹果图片的数据集，然后将其分成训练集和测试集。我们需要将苹果标记为1，非苹果标记为0。

train_dir = "path/to/training/folder"
test_dir = "path/to/testing/folder"
train_apple_dir = os.path.join(train_dir, 'apple')  
train_not_apple_dir = os.path.join(train_dir, 'not_apple')  
test_apple_dir = os.path.join(test_dir, 'apple')  
test_not_apple_dir = os.path.join(test_dir, 'not_apple')

train_apple_files = os.listdir(train_apple_dir)
train_not_apple_files = os.listdir(train_not_apple_dir)
test_apple_files = os.listdir(test_apple_dir)
test_not_apple_files = os.listdir(test_not_apple_dir)

train_images = []
train_labels = []

for file in train_apple_files:
    image_path = os.path.join(train_apple_dir, file)
    image = keras.preprocessing.image.load_img(image_path, target_size=(150, 150))
    image_array = keras.preprocessing.image.img_to_array(image)
    train_images.append(image_array)
    train_labels.append(1)
    
for file in train_not_apple_files:
    image_path = os.path.join(train_not_apple_dir, file)
    image = keras.preprocessing.image.load_img(image_path, target_size=(150, 150))
    image_array = keras.preprocessing.image.img_to_array(image)
    train_images.append(image_array)
    train_labels.append(0)
    
test_images = []
test_labels = []

for file in test_apple_files:
    image_path = os.path.join(test_apple_dir, file)
    image = keras.preprocessing.image.load_img(image_path, target_size=(150, 150))
    image_array = keras.preprocessing.image.img_to_array(image)
    test_images.append(image_array)
    test_labels.append(1)
    
for file in test_not_apple_files:
    image_path = os.path.join(test_not_apple_dir, file)
    image = keras.preprocessing.image.load_img(image_path, target_size=(150, 150))
    image_array = keras.preprocessing.image.img_to_array(image)
    test_images.append(image_array)
    test_labels.append(0)
    
train_images = np.array(train_images)
train_labels = np.array(train_labels)
test_images = np.array(test_images)
test_labels = np.array(test_labels)

接下来，我们可以定义模型。我们可以使用卷积层和池化层构建模型。在最后添加一个全连接层和输出层。我们使用ReLU激活函数和Sigmoid激活函数。

model = keras.Sequential([
    layers.Conv2D(16, 3, padding='same', activation='relu', input_shape=(150, 150 ,3)),
    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(1, activation='sigmoid')
])

接下来，我们可以编译模型，设置损失函数和优化器。

model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['accuracy'])

训练模型并输出结果。

history = model.fit(train_images, train_labels, epochs=10, validation_data=(test_images, test_labels))

test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)

print('\nTest accuracy:', test_acc)

最后，我们可以绘制训练和验证准确性的图表。

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

epochs_range = range(10)

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.xlabel('epoch')
plt.show()

以上就是基于CNN搭建苹果分类器的代码，希望能对您有所帮助。