cafar10 | kaggle | tensorflow

导包

import sklearn
import tensorflow as tf
import matplotlib as mpl
import  matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import pandas as pd
import os 
import sys
import time

from tensorflow import keras

print( tf.__version__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

数据读入

class_names = [
    'airplane',
    'automobile',
    'bird',
    'cat',
    'deer',
    'dog',
    'frog',
    'horse',
    'ship',
    'truck',
]

train_lables_file = "../input/cifar10-object-recognition-in-images-zip-file/trainLabels.csv"
test_csv_file = "../input/cifar10-object-recognition-in-images-zip-file/sampleSubmission.csv"
train_folder = "../input/cifar10-object-recognition-in-images-zip-file/train_test/train/train/"
test_folder = "../input/cifar10-object-recognition-in-images-zip-file/train_test/test/test/"

def parse_csv_file(filepath, folder):
    """Parses csv files into (filename(path), label) format"""
    results = []
    with open (filepath, 'r') as f:
        lines = f.readlines()[1:]
    for line in lines:
        image_id, label_str = line.strip('\n').split(',')
        image_full_path = os.path.join(folder, image_id + '.png')
        results.append((image_full_path, label_str))
    return results

train_label_info = parse_csv_file(train_lables_file, train_folder)
test_csv_info = parse_csv_file(test_csv_file, test_folder)

import pprint
pprint.pprint(train_label_info[0:5])
pprint.pprint(test_csv_info[0:5])
print(len(train_label_info), len(test_csv_info))

DataFrame数据读入

# 做卷积的时候所有图片的尺寸应该是一样的
height = 32
width = 32
channels = 3 
batch_size = 32
num_classes = 10

# 读取训练数据并作数据增强
# 确定一些读取格式要求
train_datagen = keras.preprocessing.image.ImageDataGenerator(
    rescale = 1./255,
    # 图片旋转的角度范围，用来数据增强
    rotation_range = 40,
    # 水平平移
    width_shift_range = 0.2,
    # 高度平移
    height_shift_range = 0.2,
    # 剪切强度
    shear_range = 0.2,
    # 缩放强度
    zoom_range = 0.2,
    # 水平翻转
    horizontal_flip = True,
    # 对图片做处理时需要填充图片，用最近的像素点填充
    fill_mode = "nearest"
)
# 读取训练数据
train_generator = train_datagen.flow_from_dataframe(
                                                    train_df,
                                                    directory = './',
                                                    x_col = 'filepath',
                                                    y_col = 'class',
                                                    classes = class_names,
                                                    target_size = (height, width),
                                                    batch_size = batch_size,
                                                    seed = 7,
                                                    shuffle = True,
                                                    clss_mode = 'sparse')

# 读取验证数据
valid_datagen = keras.preprocessing.image.ImageDataGenerator(rescale = 1./255)
valid_generator = valid_datagen.flow_from_dataframe(
                                                    valid_df,
                                                    directory = './',
                                                    x_col = 'filepath',
                                                    y_col = 'class',
                                                    classes = class_names,
                                                    target_size = (height, width),
                                                    batch_size = batch_size,
                                                    seed = 7,
                                                    shuffle = True,
                                                    clss_mode = 'sparse')
    

train_num = train_generator.samples
valid_num = valid_generator.samples
print(train_num, valid_num)

构建模型

model = keras.models.Sequential([
    keras.layers.Conv2D(filters=128, kernel_size=3, padding='same', activation='relu', input_shape=[width, height, channels]),
    keras.layers.BatchNormalization(),
    keras.layers.Conv2D(filters=128, kernel_size=3, padding='same', activation='relu'),
    keras.layers.BatchNormalization(),
    keras.layers.MaxPool2D(pool_size=2),
    
    keras.layers.Conv2D(filters=256, kernel_size=3, padding='same', activation='relu'),
    keras.layers.BatchNormalization(),
    keras.layers.Conv2D(filters=256, kernel_size=3, padding='same', activation='relu'),
    keras.layers.BatchNormalization(),
    keras.layers.MaxPool2D(pool_size=2),
    
    keras.layers.Conv2D(filters=512, kernel_size=3, padding='same', activation='relu'),
    keras.layers.BatchNormalization(),
    keras.layers.Conv2D(filters=512, kernel_size=3, padding='same', activation='relu'),
    keras.layers.BatchNormalization(),
    keras.layers.MaxPool2D(pool_size=2),
    
    keras.layers.Flatten(),
    keras.layers.Dense(512, activation='relu'),
    keras.layers.Dense(num_classes, activation='softmax')
])

model.compile(loss="sparse_categorical_crossentropy", optimizer="adam", metrics=["accuracy"])
model.summary()

训练模型

epochs = 10
history = model.fit_generator(train_generator, 
                              steps_per_epoch=train_num // batch_size, 
                              epochs=epochs, 
                              validation_data=valid_generator,
                              validation_steps=valid_num // batch_size)

可视化