kaggle 多光谱图像分类代码

以下是使用 TensorFlow 和 Keras 实现多光谱图像分类的示例代码：

首先是数据预处理部分：

import numpy as np
import pandas as pd
import cv2
import os
from sklearn.model_selection import train_test_split

# 读取数据
data = pd.read_csv('train.csv')
train_path = 'train_images/'

# 定义函数读取图像
def read_image(image_path):
    image = cv2.imread(os.path.join(train_path, image_path))
    return image

# 读取图像并将标签转换成独热编码
X = np.zeros((len(data), 256, 256, 3), dtype=np.uint8)
y = pd.get_dummies(data['label']).values

for i, image_path in enumerate(data['image']):
    X[i, :, :, :] = read_image(image_path)

# 划分训练集和验证集
X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.2, random_state=42)

接下来是模型部分，这里使用了 ResNet50：

from tensorflow.keras.applications.resnet50 import ResNet50
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D

# 定义模型
base_model = ResNet50(weights='imagenet', include_top=False, input_shape=(256, 256, 3))
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
predictions = Dense(10, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)

# 编译模型
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

最后是训练部分：

# 训练模型
model.fit(X_train, y_train, validation_data=(X_valid, y_valid), epochs=10, batch_size=32)

以上代码仅供参考，实际应用中可能需要根据具体情况进行修改和优化。