深度学习15-Google涂鸦识别挑战项目（下）

文章目录

1.数据处理
- 1)数据shuffle
- 2）TFRecord
- 3）TextLineDataset方式
- 4）from_generator方法
2.建模方法
- 例子
3.Baseline构建
- 数据处理
- 数据读取

1.数据处理

1)数据shuffle

2）TFRecord

3）TextLineDataset方式

4）from_generator方法

2.建模方法

例子

3.Baseline构建

数据处理

import json
import os
import datetime as dt
from tqdm import tqdm
import pandas as pd
import numpy as np# label
def f2cat(filename: str) -> str:return filename.split('.')[0]# 读取文件，label变成list
class Simplified():def __init__(self, input_path='./input'):self.input_path = input_pathdef list_all_categories(self):files = os.listdir(self.input_path)return sorted([f2cat(f) for f in files], key=str.lower)def read_training_csv(self, category, nrows=None, usecols=None, drawing_transform=False):df = pd.read_csv(os.path.join(self.input_path, category + '.csv'),nrows=nrows, parse_dates=['timestamp'], usecols=usecols)if drawing_transform:df['drawing'] = df['drawing'].apply(json.loads)return dfstart = dt.datetime.now()
# 加载数据路径
s = Simplified('./data/')
NCSVS = 100
# 加载类别
categories = s.list_all_categories()
print(len(categories))# tqdm显示进度
for y, cat in tqdm(enumerate(categories)):df = s.read_training_csv(cat)df['y'] = y# 构建cv，知道数据属于哪个文件df['cv'] = (df.key_id // 10 ** 7) % NCSVS # 100 # 将csv文件的1/100的数据写到里面，for循环for k in range(NCSVS):filename = './shuffle_data/train_k{}.csv'.format(k)chunk = df[df.cv == k]chunk = chunk.drop(['key_id'], axis=1)if y == 0:chunk.to_csv(filename, index=False)else:chunk.to_csv(filename, mode='a', header=False, index=False)#对csv数据打乱，进行压缩
for k in tqdm(range(NCSVS)):filename = './shuffle_data/train_k{}.csv'.format(k)if os.path.exists(filename):df = pd.read_csv(filename)df['rnd'] = np.random.rand(len(df))df = df.sort_values(by='rnd').drop('rnd', axis=1)df.to_csv('./shuffle_data_gzip/train_k{}.csv.gz'.format(k), compression='gzip', index=False)os.remove(filename)
print(df.shape)end = dt.datetime.now()
print('Latest run {}.\nTotal time {}s'.format(end, (end - start).seconds))

数据读取

import glob
import tensorflow as tf
import numpy as np
import pandas as pd
import os
import cv2
import json
import matplotlib.pyplot as plt
os.environ['CUDA_VISIBLE_DEVICES']='1'# 每一个csv.gz文件读取 -> y已经ok ->drawing 如何处理# 单通道-黑白照片
def draw_cv2(raw_strokes, size=256, lw=6, time_color=True):img = np.zeros((BASE_SIZE, BASE_SIZE), np.uint8) #画板for t, stroke in enumerate(raw_strokes):for i in range(len(stroke[0]) - 1):color = 255 - min(t, 10) * 13 if time_color else 255_ = cv2.line(img, (stroke[0][i], stroke[1][i]),(stroke[0][i + 1], stroke[1][i + 1]), color, lw)if size != BASE_SIZE:return cv2.resize(img, (size, size))else:return img# RGB图片
def draw_cv2(raw_strokes, size=256, lw=6):img = np.zeros((BASE_SIZE, BASE_SIZE, 3), np.uint8)for t, stroke in enumerate(raw_strokes):points_count = len(stroke[0]) - 1grad = 255//points_countfor i in range(len(stroke[0]) - 1):_ = cv2.line(img, (stroke[0][i], stroke[1][i]), (stroke[0][i + 1], stroke[1][i + 1]), (255, 255 - min(t,10)*13, max(255 - grad*i, 20)), lw)if size != BASE_SIZE:img = cv2.resize(img, (size, size))return imgclass DataLoader(object):def __init__(self, resize_height=64, resize_width=64, batch_size=512, fileList=None, size=256, lw=6):self.resize_height = resize_height #图片高self.resize_height = resize_height #图片宽self.batch_size = batch_size #batchself.fileList = fileList #文件数据self.size = size #画图时图片大小self.lw = lwdef __call__(self):def _generator(size,lw):while True: #for filename in np.random.permutation(self.fileList):df = pd.read_csv(filename)df['drawing'] = df['drawing'].apply(json.loads)x = np.zeros((len(df), size, size))for i, raw_strokes in enumerate(df.drawing.values):x[i] = draw_cv2(raw_strokes, size=size, lw=lw)x = x / 255.x = x.reshape((len(df), size, size, 1)).astype(np.float32)y = tf.keras.utils.to_categorical(df.y, num_classes=n_labels)for x_i,y_i in zip(x,y):yield (x_i,y_i)dataset = tf.data.Dataset.from_generator(generator=_generator,output_types=(tf.dtypes.float32, tf.dtypes.int32),output_shapes=((self.resize_height, self.resize_height, 1), (340, )),args=(self.size, self.lw))dataset = dataset.prefetch(buffer_size=10240)dataset = dataset.shuffle(buffer_size=10240).batch(self.batch_size)return dataset    DP_DIR = './shuffle_data_gzip/'BASE_SIZE = 256
n_labels = 340
np.random.seed(seed=1987)
size = 64
batchsize = 1024
# 利用正则读取文件路径
fileList = glob.glob("./shuffle_data_gzip/*.csv.gz")
train_fileList = fileList[:-1]
val_fileList = fileList[-1:]
train_ds = DataLoader(resize_height=64, resize_width=64, batch_size=batchsize, fileList=train_fileList, size=size, lw=6)()
val_ds = DataLoader(resize_height=64, resize_width=64, batch_size=batchsize, fileList=val_fileList, size=size, lw=6)()    # 建模
inputs = tf.keras.layers.Input(shape=(size, size, 1))
# include_top不用全连接层
base_model = tf.keras.applications.MobileNet(input_shape=(size, size, 1), include_top=False, weights=None, classes=n_labels)
x = base_model(inputs)
x = tf.keras.layers.Flatten()(x)
x = tf.keras.layers.Dense(1024, activation='relu')(x)
predictions = tf.keras.layers.Dense(n_labels, activation='softmax')(x)
model = tf.keras.models.Model(inputs=inputs, outputs=predictions)model.compile(optimizer=tf.keras.optimizers.Adam(lr=0.002), loss='categorical_crossentropy',metrics=[tf.keras.metrics.CategoricalCrossentropy(), tf.keras.metrics.CategoricalAccuracy(), tf.keras.metrics.TopKCategoricalAccuracy(k=3,name='top_3_categorical_accuracy')])# 训练
callbacks = [tf.keras.callbacks.ReduceLROnPlateau(monitor='val_top_3_categorical_accuracy', factor=0.75, patience=3, min_delta=0.001,mode='max', min_lr=1e-5, verbose=1),tf.keras.callbacks.ModelCheckpoint('model_all.h5', monitor='val_top_3_categorical_accuracy', mode='max', save_best_only=True,save_weights_only=True),
]model.fit(train_ds, epochs=50, verbose=1,steps_per_epoch=48500, #一个epoch用多少个step,为了快速迭代：可以设置1000。validation_data = val_ds,validation_steps = 400,callbacks = callbacks
)# 验证集测试
def apk(actual, predicted, k=3):"""Source: https://github.com/benhamner/Metrics/blob/master/Python/ml_metrics/average_precision.py"""if len(predicted) > k:predicted = predicted[:k]score = 0.0num_hits = 0.0for i, p in enumerate(predicted):if p in actual and p not in predicted[:i]:num_hits += 1.0score += num_hits / (i + 1.0)if not actual:return 0.0return score / min(len(actual), k)def mapk(actual, predicted, k=3):"""Source: https://github.com/benhamner/Metrics/blob/master/Python/ml_metrics/average_precision.py"""return np.mean([apk(a, p, k) for a, p in zip(actual, predicted)])

MobileNet论文参考

from glob import glob
import cv2
import os
import tensorflow as tf
import pandas as pd
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "2"fileList = glob("./shuffle_data_gzip/*.csv.gz") def draw_cv2(raw_strokes,BASE_SIZE=256, size=256, lw=6):img = np.zeros((BASE_SIZE, BASE_SIZE), np.uint8)for stroke in raw_strokes:for i in range(len(stroke[0]) - 1):_ = cv2.line(img, (stroke[0][i], stroke[1][i]), (stroke[0][i + 1], stroke[1][i + 1]), 255, lw)if size != BASE_SIZE:return cv2.resize(img, (size, size)) else:return imgtfrecord_file = "./tfrecord_data/train.tfrecords"with tf.io.TFRecordWriter(tfrecord_file) as writer:for filename in fileList[:1]:df = pd.read_csv(filename)df['drawing'] = df['drawing'].apply(json.loads)for row in range(df.shape[0]):drawing = df.loc[row,'drawing']img = draw_cv2(drawing,BASE_SIZE=128, size=128, lw=6)img = img.tostring()label = df.loc[row,'y']# 建立 tf.train.Feature 字典feature = {                             'image': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img])),  # 图片是一个 Bytes 对象'label': tf.train.Feature(int64_list=tf.train.Int64List(value=[label]))   # 标签是一个 Int 对象}example = tf.train.Example(features=tf.train.Features(feature=feature)) # 通过字典建立 Examplewriter.write(example.SerializeToString())   # 将Example序列化并写入 TFRecord 文件# 读取 TFRecord 文件
raw_dataset = tf.data.TFRecordDataset(tfrecord_file)
# 定义Feature结构，告诉解码器每个Feature的类型是什么
feature_description = { 'image': tf.io.FixedLenFeature([], tf.string),'label': tf.io.FixedLenFeature([], tf.int64),
}# 将 TFRecord 文件中的每一个序列化的 tf.train.Example 解码
def _parse_example(example_string): feature_dict = tf.io.parse_single_example(example_string, feature_description)image = tf.io.decode_raw(feature_dict['image'], tf.uint8)    # 解码JPEG图片image = tf.reshape(image, [128,128,1])image = tf.dtypes.cast(image,tf.float32)image = image / 255.0label = tf.one_hot(feature_dict['label'],depth=340)return image, labeldataset = raw_dataset.map(_parse_example)train_ds = dataset.prefetch(buffer_size=tf.data.experimental.AUTOTUNE).shuffle(buffer_size=tf.data.experimental.AUTOTUNE).batch(1024)class MobileNetModel(tf.keras.models.Model):def __init__(self, size, n_labels, **kwargs):super(MobileNetModel, self).__init__(**kwargs)# 预训练模型self.base_model = tf.keras.applications.MobileNet(input_shape=(size, size, 1), include_top=False, weights=None, classes=n_labels)self.flatten = tf.keras.layers.Flatten()self.dense = tf.keras.layers.Dense(1024, activation='relu')self.outputs =  tf.keras.layers.Dense(n_labels, activation='softmax')def call(self, inputs):x = self.base_model(inputs)x = self.flatten(x)x = self.dense(x)output_ = self.outputs(x)return output_model = MobileNetModel(size=128,n_labels=340)loss_object = tf.keras.losses.CategoricalCrossentropy()learning_rate = 0.001
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(name='train_accuracy')
train_top3_accuracy = tf.keras.metrics.TopKCategoricalAccuracy(k=3,name='train_top_3_categorical_accuracy')test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')
test_top3_accuracy = tf.keras.metrics.TopKCategoricalAccuracy(k=3,name='test_top_3_categorical_accuracy')# @tf.function
def train_one_step(images, labels):with tf.GradientTape() as tape:predictions = model(images)loss = loss_object(labels, predictions)gradients = tape.gradient(loss, model.trainable_variables)optimizer.apply_gradients(zip(gradients, model.trainable_variables))train_loss(loss)train_accuracy(labels, predictions)train_top3_accuracy(labels, predictions)def val_one_step(images, labels):predictions = model(images)t_loss = loss_object(labels, predictions)test_loss(t_loss)test_accuracy(labels, predictions)test_top3_accuracy(labels, predictions)EPOCHS=10
for epoch in range(EPOCHS):# 在下一个epoch开始时，重置评估指标train_loss.reset_states()train_accuracy.reset_states()train_top3_accuracy.reset_states()test_loss.reset_states()test_accuracy.reset_states()test_top3_accuracy.reset_states()for step,(images, labels) in enumerate(train_ds):train_one_step(images, labels)if step % 200 == 0:print("step:{0}; Samples:{1}; Train Loss:{2}; Train Accuracy:{3},Train Top3 Accuracy:{4}".format(step, (step + 1) * 1024, train_loss.result(), train_accuracy.result()*100, train_top3_accuracy.result()*100))template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy{}'
print(template.format(epoch + 1,train_loss.result(),train_accuracy.result() * 100,train_top3_accuracy()*100,test_loss.result(),test_accuracy.result() * 100,test_top3_accuracy()*100))

深度学习15-Google涂鸦识别挑战项目（下）相关推荐

【人工智能项目】深度学习实现汉字书法识别
[人工智能项目]深度学习实现汉字书法识别背景介绍竞赛数据提供100个汉字书法单字,包括碑帖,手写书法,古汉字等.图片全部为单通道宽度jpg,宽高不定. 数据集介绍训练集:每个汉字400张图片,共 ...
基于深度学习的命名实体识别研究综述——论文研读
基于深度学习的命名实体识别研究综述摘要: 0引言 1基于深度学习的命名实体识别方法 1.1基于卷积神经网络的命名实体识别方法 1.2基于循环神经网络的命名实体识别方法 1.3基于Transforme ...
【深度学习】OCR文本识别
OCR文字识别定义 OCR(optical character recognition)文字识别是指电子设备(例如扫描仪或数码相机)检查纸上打印的字符,然后用字符识别方法将形状翻译成计算机文字的过程: ...
NLP入门（五）用深度学习实现命名实体识别（NER）
前言在文章:NLP入门(四)命名实体识别(NER)中,笔者介绍了两个实现命名实体识别的工具--NLTK和Stanford NLP.在本文中,我们将会学习到如何使用深度学习工具来自己一步步地实现N ...
一种基于深度学习的增值税发票影像识别系统
一种基于深度学习的增值税发票影像识别系统-专利技术交底书缩略语和关键术语定义 1.卷积神经网络(Convolutional Neural Networks, CNN)是一类包含卷积计算且具有深度结构 ...
基于深度学习的人脸性别识别系统（含UI界面，Python代码）
摘要:人脸性别识别是人脸识别领域的一个热门方向,本文详细介绍基于深度学习的人脸性别识别系统,在介绍算法原理的同时,给出Python的实现代码以及PyQt的UI界面.在界面中可以选择人脸图片.视频进行检 ...
一文掌握基于深度学习的人脸表情识别开发（基于PaddlePaddle）
目录一.概述 1.1 表情分类 1.2 表情识别方法 1.2.1 人工特征方法 1.2.2 神经网络方法 1.3 本文实现二.环境准备 2.1 安装PaddlePaddle 2.2 安装Paddl ...
表单识别（四）-基于深度学习的表单识别)-OCR
(论文研读后,感觉有用的一些笔记,主要是给自己记录) 论文:熊雨点,基于深度学习的表单识别系统的研究与实现基于深度学习的表单识别前言: 文档检测方法: 基于扩张卷积残差网络的表单文档定位方法: 扩 ...
浙江大学《深度学习与行人重识别》课程课件
点击上方,选择星标或置顶,不定期资源大放送! 阅读大概需要3分钟 Follow小博主,每天更新前沿干货课程介绍该课程为浙江大学罗浩博士于2018年10月录制的<基于深度学习和行人重识别> ...
opencv交通标志识别_教你从零开始做一个基于深度学习的交通标志识别系统
教你从零开始做一个基于深度学习的交通标志识别系统基于Yolo v3的交通标志识别系统及源码自动驾驶之--交通标志识别在本文章你可以学习到如何训练自己采集的数据集,生成模型,并用yolo v3算法 ...

深度学习15-Google涂鸦识别挑战项目（下）

文章目录

1.数据处理

1)数据shuffle

2）TFRecord

3）TextLineDataset方式

4）from_generator方法

2.建模方法

例子

3.Baseline构建

数据处理

数据读取

深度学习15-Google涂鸦识别挑战项目（下）相关推荐

最新文章

热门文章