划分数据集导入keras

最新推荐文章于 2024-08-26 10:20:15 发布

tominent

最新推荐文章于 2024-08-26 10:20:15 发布

阅读量1.4k

点赞数

本文链接：https://blog.csdn.net/tominent/article/details/85988224

版权

本文介绍了如何利用os.walk()函数和pandas库对UCMerced遥感数据集进行划分，以适应深度学习模型如keras的训练需求。

摘要由CSDN通过智能技术生成

第一种用os.walk()函数以遥感数据集 UCMerced 为例

from contextlib import suppress
import matplotlib
import matplotlib.pyplot as plt

import numpy as np
import os
import warnings
from zipfile import ZipFile

from skimage.io import imread, imsave

from keras import applications
from keras import optimizers
from keras.models import Sequential
from keras.layers import Activation, Dense, Dropout, Flatten
from keras.utils import to_categorical
from keras.preprocessing.image import ImageDataGenerator

from sklearn.metrics import accuracy_score, classification_report

# # Data Preparation

# ### Download the [UC Merced Land Use dataset](http://vision.ucmerced.edu/datasets/landuse.html)

# In[2]: 建立文件夹

source_dir = (r'D:\tang\jiangxia\sun\jinzhou\data\erjifenlei')

# Set random seed for reproducibility
np.random.seed(8)

# ### Randomly assign each image to train, validate, or test folder, segregated by class name

# In[5]:

"""
C