tflearn 中文汉字识别模型试验汇总

def get_model(width, height, classes=40):

    # TODO, modify model

    # Building 'VGG Network'

    network = input_data(shape=[None, width, height, 1])  # if RGB, 224,224,3

    network = conv_2d(network, 64, 3, activation='relu')

    #network = conv_2d(network, 64, 3, activation='relu')

    network = max_pool_2d(network, 2, strides=2)

    network = conv_2d(network, 128, 3, activation='relu')

    #network = conv_2d(network, 128, 3, activation='relu')

    network = max_pool_2d(network, 2, strides=2)

    network = conv_2d(network, 256, 3, activation='relu')

    #network = conv_2d(network, 256, 3, activation='relu')

    #network = conv_2d(network, 256, 3, activation='relu')

    network = max_pool_2d(network, 2, strides=2)

    network = conv_2d(network, 512, 3, 2, activation='relu')

    # network = conv_2d(network, 512, 3, activation='relu')

    # network = conv_2d(network, 512, 3, activation='relu')

    # network = max_pool_2d(network, 2, strides=2)

    # network = conv_2d(network, 512, 3, activation='relu')

    # network = conv_2d(network, 512, 3, activation='relu')

    # network = conv_2d(network, 512, 3, activation='relu')

    network = max_pool_2d(network, 2, strides=2)

    # network = fully_connected(network, 4096, activation='relu')

    # network = dropout(network, 0.5)

    #network = fully_connected(network, 1024, activation='relu')

    network = fully_connected(network, 2048, activation='relu')

    network = dropout(network, 0.8)

    network = fully_connected(network, classes, activation='softmax')

    network = regression(network, optimizer='rmsprop',

                         loss='categorical_crossentropy',

                         learning_rate=0.0001)

    model = tflearn.DNN(network, checkpoint_path='checkpoint',

                        max_checkpoints=1, tensorboard_verbose=1)

    return model

if __name__ == "__main__":

    width, height = 32, 32

    X, Y, org_labels = load_data(dirname="data", resize_pics=(width, height))

    trainX, testX, trainY, testY = train_test_split(X, Y, test_size=0.2, random_state=666)

    print("sample data:")

    print(trainX[0])

    print(trainY[0])

    print(testX[-1])

    print(testY[-1])

    model = get_model(width, height, classes=100)

    filename = 'cnn_handwrite-acc0.8.tflearn'

    # try to load model and resume training

    #try:

    #    model.load(filename)

    #    print("Model loaded OK. Resume training!")

    #except:

    #    pass

    # Initialize our callback with desired accuracy threshold.

    early_stopping_cb = EarlyStoppingCallback(val_acc_thresh=0.9)

    try:

        model.fit(trainX, trainY, validation_set=(testX, testY), n_epoch=500, shuffle=True,

                  snapshot_epoch=True, # Snapshot (save & evaluate) model every epoch.

                  show_metric=True, batch_size=32, callbacks=early_stopping_cb, run_id='cnn_handwrite')

    except StopIteration as e:

        print("OK, stop iterate!Good!")

    model.save(filename)

    # predict all data and calculate confusion_matrix

    model.load(filename)

    pro_arr =model.predict(X)

    predict_labels = np.argmax(pro_arr, axis=1)

    print(classification_report(org_labels, predict_labels))

    print(confusion_matrix(org_labels, predict_labels))

上述模型效果：

。。。

试试mnist直接拿过来：

def get_model(width, height, classes=40):

    # TODO, modify model

    # Real-time data preprocessing

    img_prep = tflearn.ImagePreprocessing()

    img_prep.add_featurewise_zero_center(per_channel=True)

    network = input_data(shape=[None, width, height, 1]) #, data_preprocessing=img_prep)  # if RGB, 224,224,3

    network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")

    network = max_pool_2d(network, 2)

    network = local_response_normalization(network)

    network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")

    network = max_pool_2d(network, 2)

    network = local_response_normalization(network)

    network = fully_connected(network, 128, activation='tanh')

    network = dropout(network, 0.8)

    network = fully_connected(network, 256, activation='tanh')

    network = dropout(network, 0.8)

    network = fully_connected(network, classes, activation='softmax')

    network = regression(network, optimizer='adam', learning_rate=0.01,

                         loss='categorical_crossentropy', name='target')

    # Training

    model = tflearn.DNN(network, tensorboard_verbose=0)

    return model

模型效果：很难收敛！！！

接下来看看其他模型：

def get_model(width, height, classes=40):

    # TODO, modify model

    # Building 'VGG Network'

    network = input_data(shape=[None, width, height, 1])  # if RGB, 224,224,3

    network = conv_2d(network, 64, 3, activation='relu')

    #network = conv_2d(network, 64, 3, activation='relu')

    network = max_pool_2d(network, 2, strides=2)

    network = conv_2d(network, 128, 3, activation='relu')

    #network = conv_2d(network, 128, 3, activation='relu')

    network = max_pool_2d(network, 2, strides=2)

    netword = tflearn.batch_normalization(network)

    network = fully_connected(network, 1024, activation='relu')

    network = dropout(network, 0.8)

    network = fully_connected(network, classes, activation='softmax')

    network = regression(network, optimizer='rmsprop',

                         loss='categorical_crossentropy',

                         learning_rate=0.0001)

    model = tflearn.DNN(network, checkpoint_path='checkpoint',

                        max_checkpoints=1, tensorboard_verbose=1)

    return model

上述模型效果：

Inception模型：

def get_model(width, height, classes=40):

    # TODO, modify model

    # Building 'VGG Network'

    network = input_data(shape=[None, width, height, 1])  # if RGB, 224,224,3

    network = conv_2d(network, 64, 3, activation='relu')

    inception_3b_1_1 = conv_2d(network, 64, filter_size=1, activation='relu', name='inception_3b_1_1')

    inception_3b_3_3 = conv_2d(network, 64, filter_size=3, activation='relu', name='inception_3b_3_3')

    inception_3b_5_5 = conv_2d(network, 64, filter_size=5, activation='relu', name='inception_3b_5_5')

    inception_3b_output = merge([inception_3b_1_1, inception_3b_3_3, inception_3b_5_5], mode='concat', axis=3, name='inception_3b_output')

    network = max_pool_2d(inception_3b_output, kernel_size=3, strides=2, name='pool3_3_3')

    network = dropout(network, 0.4)

    network = fully_connected(network, classes, activation='softmax')

    network = regression(network, optimizer='momentum',

                     loss='categorical_crossentropy',

                     learning_rate=0.001)

    #network = regression(network, optimizer='rmsprop',

    #                     loss='categorical_crossentropy',

    #                     learning_rate=0.0001)

    model = tflearn.DNN(network, checkpoint_path='checkpoint',

                        max_checkpoints=1, tensorboard_verbose=1)

    return model

上述模型效果：

--

Training Step: 597  | total loss: 4.36442 | time: 342.271ss

| Momentum | epoch: 001 | loss: 4.36442 - acc: 0.0578 | val_loss: 4.30726 - val_acc: 0.1274 -- iter: 19094/19094

--

Terminating training at the end of epoch 1

Training Step: 1193  | total loss: 3.02893 | time: 322.366ss

Training Step: 1194  | total loss: 3.00916 | time: 339.206ser: 19072/19094

| Momentum | epoch: 002 | loss: 3.00916 - acc: 0.2988 | val_loss: 2.71907 - val_acc: 0.4845 -- iter: 19094/19094

--

Terminating training at the end of epoch 2

Training Step: 1791  | total loss: 2.23406 | time: 347.633ss

| Momentum | epoch: 003 | loss: 2.23406 - acc: 0.4559 | val_loss: 1.84004 - val_acc: 0.5888 -- iter: 19094/19094

换成avg pool跑起来很慢：

    #network = max_pool_2d(inception_3b_output, kernel_size=3, strides=2, name='pool3_3_3')

    network = avg_pool_2d(inception_3b_output, kernel_size=7, strides=1) # acc: 0.0217 | val_loss: 4.50712 - val_acc: 0.0630 -- iter: 19094/19094

花费时间长，而且看不到什么效果：

resnet结构：

def get_model(width, height, classes=40):

    # TODO, modify model

    # Building 'VGG Network'

    network = input_data(shape=[None, width, height, 1])  # if RGB, 224,224,3

    # Residual blocks

    # 32 layers: n=5, 56 layers: n=9, 110 layers: n=18

    n = 2

    net = tflearn.conv_2d(network, 16, 3, regularizer='L2', weight_decay=0.0001)

    net = tflearn.residual_block(net, n, 16)

    net = tflearn.residual_block(net, 1, 32, downsample=True)

    net = tflearn.residual_block(net, n-1, 32)

    net = tflearn.residual_block(net, 1, 64, downsample=True)

    net = tflearn.residual_block(net, n-1, 64)

    net = tflearn.batch_normalization(net)

    net = tflearn.activation(net, 'relu')

    net = tflearn.global_avg_pool(net)

    # Regression

    net = tflearn.fully_connected(net, classes, activation='softmax')

    mom = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)

    net = tflearn.regression(net, optimizer=mom,

                             loss='categorical_crossentropy')

    # Training

    model = tflearn.DNN(net, checkpoint_path='model_resnet_cifar10',

                        max_checkpoints=10, tensorboard_verbose=0,

                        clip_gradients=0.)

    return model

--
Terminating training at the end of epoch 7
Training Step: 4776 | total loss: 0.13311 | time: 132.182ss
| Momentum | epoch: 008 | loss: 0.13311 - acc: 0.9561 | val_loss: 0.22734 - val_acc: 0.9370 -- iter: 19094/19094
--
Terminating training at the end of epoch 8
Successfully left training! Final model accuracy: 0.95614439249
OK, stop iterate!Good!
avg / total 0.97 0.96 0.96 23868

resnet加深结构：

def get_model(width, height, classes=40):

    # TODO, modify model

    # Building 'VGG Network'

    network = input_data(shape=[None, width, height, 1])  # if RGB, 224,224,3

    # Building Residual Network

    net = tflearn.conv_2d(network, 64, 3, activation='relu', bias=False)

    # Residual blocks

    net = tflearn.residual_bottleneck(net, 3, 16, 64)

    net = tflearn.residual_bottleneck(net, 1, 32, 128, downsample=True)

    net = tflearn.residual_bottleneck(net, 2, 32, 128)

    net = tflearn.residual_bottleneck(net, 1, 64, 256, downsample=True)

    net = tflearn.residual_bottleneck(net, 2, 64, 256)

    net = tflearn.batch_normalization(net)

    net = tflearn.activation(net, 'relu')

    net = tflearn.global_avg_pool(net)

    # Regression

    net = tflearn.fully_connected(net, classes, activation='softmax')

    net = tflearn.regression(net, optimizer='momentum',

                             loss='categorical_crossentropy',

                             learning_rate=0.1)

    # Training

    model = tflearn.DNN(net, checkpoint_path='model_resnet_mnist',

                        max_checkpoints=10, tensorboard_verbose=0)

    return model

结果是训练的时间更久了。

--
Terminating training at the end of epoch 5
Training Step: 3582 | total loss: 0.14701 | time: 313.084s
| Momentum | epoch: 006 | loss: 0.14701 - acc: 0.9516 | val_loss: 0.30464 - val_acc: 0.9103 -- iter: 19094/19094
--
Terminating training at the end of epoch 6
Successfully left training! Final model accuracy: 0.951571881771
OK, stop iterate!Good!

avg / total 0.94 0.93 0.93 23868

resnet加入预处理：

def get_model(width, height, classes=40):

    # TODO, modify model

    # Real-time data preprocessing

    img_prep = tflearn.ImagePreprocessing()

    img_prep.add_featurewise_zero_center(per_channel=True)

    network = input_data(shape=[None, width, height, 1], data_preprocessing=img_prep)  # if RGB, 224,224,3

    ...

效果：也还是很不错！

--

 Training Step: 597  | total loss: 1.12591 | time: 312.814s

| Momentum | epoch: 001 | loss: 1.12591 - acc: 0.6664 | val_loss: 1.86609 - val_acc: 0.5209 -- iter: 19094/19094

--

Terminating training at the end of epoch 1

 Training Step: 1194  | total loss: 0.61108 | time: 312.415s

| Momentum | epoch: 002 | loss: 0.61108 - acc: 0.8291 | val_loss: 0.56165 - val_acc: 0.8395 -- iter: 19094/19094

highway模型：又快又好！

def get_model(width, height, classes=40):

    # TODO, modify model

    network = input_data(shape=[None, width, height, 1])  # if RGB, 224,224,3

    # Building convolutional network

    #highway convolutions with pooling and dropout

    for i in range(3):

        for j in [3, 2, 1]:

            network = highway_conv_2d(network, 16, j, activation='elu')

        network = max_pool_2d(network, 2)

        network = batch_normalization(network)

    network = fully_connected(network, 128, activation='elu')

    network = fully_connected(network, 256, activation='elu')

    network = fully_connected(network, classes, activation='softmax')

    network = regression(network, optimizer='adam', learning_rate=0.01,

                         loss='categorical_crossentropy', name='target')

    model = tflearn.DNN(network, tensorboard_verbose=0)

    return model

最后看看cifar10模型效果：

def get_model(width, height, classes=40):

    # TODO, modify model

    # Real-time data preprocessing

    img_prep = tflearn.ImagePreprocessing()

    img_prep.add_featurewise_zero_center(per_channel=True)

    img_prep.add_featurewise_stdnorm()

    network = input_data(shape=[None, width, height, 1], data_preprocessing=img_prep)  # if RGB, 224,224,3

    network = conv_2d(network, 32, 3, activation='relu')

    network = max_pool_2d(network, 2)

    network = conv_2d(network, 64, 3, activation='relu')

    network = conv_2d(network, 64, 3, activation='relu')

    network = max_pool_2d(network, 2)

    network = fully_connected(network, 512, activation='relu')

    network = dropout(network, 0.5)

    network = fully_connected(network, classes, activation='softmax')

    network = regression(network, optimizer='adam',

                         loss='categorical_crossentropy',

                         learning_rate=0.001)

    model = tflearn.DNN(network, tensorboard_verbose=0)

    return model

效果也很不错！又快又好：

densenet效果

def get_model(width, height, classes=40):

    # Growth Rate (12, 16, 32, ...)

    k = 12

    # Depth (40, 100, ...)

    L = 40

    nb_layers = int((L - 4) / 3)

    network = input_data(shape=[None, width, height, 1])

    net = tflearn.conv_2d(network, 16, 3, regularizer='L2', weight_decay=0.0001)

    net = tflearn.densenet_block(net, nb_layers, k)

    net = tflearn.densenet_block(net, nb_layers, k)

    net = tflearn.densenet_block(net, nb_layers, k)

    net = tflearn.global_avg_pool(net)

    # Regression

    net = tflearn.fully_connected(net, classes, activation='softmax')

    opt = tflearn.Nesterov(0.1, lr_decay=0.1, decay_step=32000, staircase=True)

    net = tflearn.regression(net, optimizer=opt,

                             loss='categorical_crossentropy')

    # Training

    model = tflearn.DNN(net, checkpoint_path='model_densenet_cifar10',

                        max_checkpoints=10, tensorboard_verbose=0, clip_gradients=0.)

    return model

resnext 模型：

def get_model(width, height, classes=40):

    # TODO, modify model

    # Real-time data preprocessing

    img_prep = tflearn.ImagePreprocessing()

    img_prep.add_featurewise_zero_center(per_channel=True)

    img_prep.add_featurewise_stdnorm()

    network = input_data(shape=[None, width, height, 1], data_preprocessing=img_prep)  # if RGB, 224,224,3

    n = 2

    net = tflearn.conv_2d(network, 16, 3, regularizer='L2', weight_decay=0.0001)

    net = tflearn.resnext_block(net, n, 16, 32)

    net = tflearn.resnext_block(net, 1, 32, 32, downsample=True)

    net = tflearn.resnext_block(net, n-1, 32, 32)

    net = tflearn.resnext_block(net, 1, 64, 32, downsample=True)

    net = tflearn.resnext_block(net, n-1, 64, 32)

    net = tflearn.batch_normalization(net)

    net = tflearn.activation(net, 'relu')

    net = tflearn.global_avg_pool(net)

    # Regression

    net = tflearn.fully_connected(net, classes, activation='softmax')

    opt = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)

    net = tflearn.regression(net, optimizer=opt,

                             loss='categorical_crossentropy')

    # Training

    model = tflearn.DNN(net, checkpoint_path='model_resnext_cifar10',

                        max_checkpoints=10, tensorboard_verbose=0, clip_gradients=0.)

    return model

tflearn 中文汉字识别模型试验汇总的更多相关文章

tflearn 中文汉字识别，训练后模型存为pb给TensorFlow使用——模型层次太深，或者太复杂训练时候都不会收敛
tflearn 中文汉字识别,训练后模型存为pb给TensorFlow使用. 数据目录在data,data下放了汉字识别图片: data$ ls0 1 10 11 12 13 14 15 ...
Eclipse中文乱码解决汇总（应该比较全）：
Eclipse中文乱码解决汇总(应该比较全,欢迎补充): 方法一: 把GBK改成utf-8. 方法二: Window->preference->general->content ty ...
ST官方翻译的中文应用笔记汇总
ST官方翻译的中文应用笔记汇总 http://www.51hei.com/stm32/3382.html 官方中文AN:AN3116:STM32? 的 ADC 模式及其应用AN1015:用于提高微控制 ...
PTA数据结构与算法题目集(中文) 7-41PAT排名汇总 (25 分)
PTA数据结构与算法题目集(中文) 7-41PAT排名汇总 (25 分) 7-41 PAT排名汇总 (25 分) 计算机程序设计能力考试(Programming Ability Test,简称P ...
苹果Swift语言中文教程资源汇总
苹果swift语言中文教程(零)搭配环境以及代码执行成功http://vjiazhi.com/kaifa/1014.html 苹果Swift语言中文教程(一)基础数据类型 http://vjiazhi ...
一周学会Mootools 1.4中文教程:(7)汇总收尾
转眼之间已经第七课了,这也将成为最后一课,如果这7课下来您感觉水平没有达到预想的水平,没关系您可以继续关注本站的博文,我会陆续发一些类似的文章帮您提升水平,另外我最近打算和群里的几个Mootools爱 ...
转：git windows中文乱码问题解决汇总
it的Windows版本Msysgit对中文的支持不够好 .当使用时,会出现以下三种情况的中文乱码: 下面的几个文件都在git安装目录下文件夹etc内.1.ls不能显示中文目录解决办法:在git/g ...
tomcat7.0在centos7下中文乱码问题解决汇总
1. 系统级的中文设置 Centos7跟之前的6和5安装的中文字符命令都不一样 [root@iZ25bdzgev8Z ~]# locale #查看当前系统的语言环境 [root@iZ25bdzgev8 ...
CloudNotes之桌面客户端篇：插件系统的实现
[CloudNotes版本更新历史与各版本下载地址请点击此处] [CloudNotes中文系列文章汇总列表请点击此处] [查看CloudNotes源代码请点击此处] 有时候,同一个名词,针对不同的人群 ...

随机推荐

Handler处理机制
handler缺点:如果要运送两种类型的数据(比如一个Bitmap,一个Object)就不能运送,但可以用Bunder来传输 * 使用handler的步骤: * 1.创建一个handl ...
iOS -- SKTransition类
SKTransition类继承自 NSObject 符合 NSObject(NSObject) 框架 /System/Library/Frameworks/SpriteKit.framewor ...
mysql 导入sql文件时自动切换了大小写
windows环境下: 解决办法(即将其改为大小写敏感): 在my.ini中添加 lower_case_table_names=1
-webkit-transform:translate3d(0,0,0)触发GPU加速，让网页动画更流畅
前段时间,依照美拍的视频效果写了一个效果类似的网页版的动画. 电脑上安装了三种浏览器:IE.Chrome.Firefox.分别作了測试,结果显示Chrome在这方面的渲染效果最差.常常出现卡顿现象.f ...
xpages很不错的demo
之前有上传了xpages的样例,如今统一把地址发出来,希望对学习xpages的朋友有帮助 1)这是主要的教程,在没有扩展库之前的教程,假设能熟练使用这个样例已经够了,加上你有html,js,css的功 ...
python（27）- 面向对象练习Ⅰ
一:定义如下类,并最大程度地重用代码(继承,派生:子类重用父类方法,组合) 老师类学生类分数类课程类生日类 class People: def __init__(self,name,age,b ...
Codeforces 490F Treeland Tour 树上的最长上升子序列
题目链接:点击打开链接题意: 给定n个点的树. 以下n个数表示点权. 以下n-1行给出树. 找一条链,然后找出这条链中的点权组成的最长上升子序列. 求:最长上升子序列的长度. 思路: 首先是维护一条 ...
笔记09 WS，WCF
http://blog.csdn.net/avi9111/article/details/5655563 http://www.cnblogs.com/tearer/archive/2013/04/2 ...
some cmds,tools and utils man
NAME stdbuf - Run COMMAND, with modified buffering operations for its standard streams. SYNOPSIS std ...
UVA11770 - Lighting Away
题目链接题意:一个有向图,每对一个结点操作.就能够触发连锁反应,使得该结点及它直接或间接指向的点均获得标记,问至少须要操作多少个结点使得全部结点获得标记思路:有向图的强连通分量.用Tarjan缩点 ...

tflearn 中文汉字识别模型试验汇总

tflearn 中文汉字识别模型试验汇总的更多相关文章

随机推荐

热门专题