import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
import os
import pandas as pd
import sklearn
import sys
import tensorflow as tf
import timefrom tensorflow import keras
from PIL import Image%matplotlib inline
print(tf.__version__)
2.0.0-alpha0
train_dir = "./input/training"
valid_dir = "./input/validation"
label_file = "./input/monkey_labels.txt"
print(os.path.exists(train_dir))
print(os.path.exists(valid_dir))
print(os.path.exists(label_file))print(os.listdir(train_dir))
print(os.listdir(valid_dir))
True
True
True
['n0', 'n1', 'n2', 'n3', 'n4', 'n5', 'n6', 'n7', 'n8', 'n9']
['n0', 'n1', 'n2', 'n3', 'n4', 'n5', 'n6', 'n7', 'n8', 'n9']
# resnet处理的图像大小为(224,224)
height = 224
width = 224
channels = 3
batch_size = 24
num_classes = 10# keras.preprocessing.image.ImageDataGenerator:图像数据生成器,用于数据增强
train_datagen = keras.preprocessing.image.ImageDataGenerator(
preprocessing_function = keras.applications.resnet50.preprocess_input,
rotation_range = 40,
width_shift_range = 0.2,
height_shift