使用VGG-16做kaggle cats vs dogs 图像分类

最新推荐文章于 2024-08-01 11:29:54 发布

耶巴蒂

最新推荐文章于 2024-08-01 11:29:54 发布

阅读量2k

点赞数 3

分类专栏：图像识别练习

本文链接：https://blog.csdn.net/baidu_41703242/article/details/83032369

版权

本文展示了如何运用VGG-16模型参与Kaggle上的猫狗图像分类竞赛。通过训练代码和测试代码的执行，得到了训练结果和测试结果。

摘要由CSDN通过智能技术生成

直接上代码

from keras.preprocessing.image import ImageDataGenerator
from keras import optimizers
import keras
import os
from keras import models
from keras import layers
from tensorflow.keras.callbacks import TensorBoard
from keras.applications import VGG16

original_dataset_dir = '/home/ysy/tf_keras_learning/kagglecatsanddogs_3367a (1)'

# Directories for our training,
# validation and test splits
train_dir = os.path.join(original_dataset_dir, 'train')
#os.mkdir(train_dir)
validation_dir = os.path.join(original_dataset_dir, 'validation')
#os.mkdir(validation_dir)
test_dir = os.path.join(original_dataset_dir, 'test')
#os.mkdir(test_dir)

# Directory with our training cat pictures
train_cats_dir = os.path.join(train_dir, 'cats')
#os.mkdir(train_cats_dir)

# Directory with our training dog pictures
train_dogs_dir = os.path.join(train_dir, 'dogs')
#os.mkdir(train_dogs_