[Tensorflow][轉載]cifar10數據集模型搭建與訓練

原創

FL1623863129

2020-07-07 04:49

# To add a new cell, type '# %%'

# To add a new markdown cell, type '# %% [markdown]'

# %%

from IPython import get_ipython

# %%

get_ipython().run_line_magic('matplotlib', 'inline')

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 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__)

# %%

class_names = [

'airplane',

'automobile',

'bird',

'cat',

'deer',

'dog',

'frog',

'horse',

'ship',

'truck',

]

train_lables_file = './cifar10/trainLabels.csv'

test_csv_file = './cifar10/sampleSubmission.csv'

train_folder = './cifar10/train/'

test_folder = './cifar10/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_labels_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_labels_info[0:5])

pprint.pprint(test_csv_info[0:5])

print(len(train_labels_info), len(test_csv_info))

# %%

# train_df = pd.DataFrame(train_labels_info)

train_df = pd.DataFrame(train_labels_info[0:45000])

valid_df = pd.DataFrame(train_labels_info[45000:])

test_df = pd.DataFrame(test_csv_info)

train_df.columns = ['filepath', 'class']

valid_df.columns = ['filepath', 'class']

test_df.columns = ['filepath', 'class']

print(train_df.head())

print(valid_df.head())

print(test_df.head())

# %%

height = 32

width = 32

channels = 3

batch_size = 32

num_classes = 10

train_datagen = keras.preprocessing.image.ImageDataGenerator(

rescale = 1./255,

rotation_range = 40,

width_shift_range = 0.2,

height_shift_range = 0.2,

shear_range = 0.2,

zoom_range = 0.2,

horizontal_flip = True,

fill_mode = 'nearest',

)

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,

class_mode = 'sparse',

)

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 = False,

class_mode = "sparse")

train_num = train_generator.samples

valid_num = valid_generator.samples

print(train_num, valid_num)

# %%

for i in range(2):

x, y = train_generator.next()

print(x.shape, y.shape)

print(y)

# %%

model = keras.models.Sequential([

keras.layers.Conv2D(filters=128, kernel_size=3, padding='same',

activation='relu',

input_shape=[width, height, channels]),