宣传展示型网站设计,电脑公司网站设计,wordpress 启用多站点,网站被k前言
上一节学习了以TensorFlow为底端的keras接口最简单的使用#xff0c;这里就继续学习怎么写卷积分类模型和各种保存方法(仅保存权重、权重和网络结构同时保存)
国际惯例#xff0c;参考博客#xff1a; 官方教程 【注】其实不用看博客#xff0c;直接翻到文末看我的c…前言
上一节学习了以TensorFlow为底端的keras接口最简单的使用这里就继续学习怎么写卷积分类模型和各种保存方法(仅保存权重、权重和网络结构同时保存)
国际惯例参考博客 官方教程 【注】其实不用看博客直接翻到文末看我的colab就行里面涵盖了学习方法包括自己的出错内容和一些简单笔记下面为了展示方便每次都重新定义了网络结构对Python熟悉的大佬可以直接def create_model():函数把模型结构保存起来后面直接调用就行
构建卷积模型分类
回顾一下上篇博客介绍的构建模型方法有两种写法
model keras.models.Sequential([keras.layers.Flatten(...),keras.layers.Dense(...),...
])model keras.models.Sequential()
model.add(keras.layers.Flatten(...))
model.add(keras.layers.Dense(...))
])第一种简单第二种舒服本博文采用第二种写法构建一个简单的卷积网络
引入相关包
保存模型需要路径(引入os)数据归一化处理(引入numpy)此外注意虽然我们学习keras,但是不仅要引入keras还得引入tensorflow具体原因后续再说
import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
import os构建数据集
还是用mnist吧后续根据需要出一个训练本地图片数据的教程看看是不是还得数据流操作 注意要把标签改为单热度编码格式数据也得归一化
mnist_dataset keras.datasets.mnist
(train_x,train_y),(test_x,test_y) mnist_dataset.load_data()
train_y keras.utils.to_categorical(train_y,10)
test_y keras.utils.to_categorical(test_y,10)
train_x train_x / 255.0
test_x test_x / 255.0还得注意就是keras的卷积操作接受的数据是一个思维矩阵需要指定是channels_first即样本通道行列, 还是channels_last即样本行列通道默认最后的维度是通道(channels_last)
train_x train_x[ ..., np.newaxis ]
test_x test_x[..., np.newaxis ]
print(train_x.shape)#(60000, 28, 28, 1)构建模型
构建简单的AlexNet,但是直接用这个结构可能有问题因为输入图片总共28\*28经过多次卷积池化会越变越小最后可能都不够做卷积池化了为稍微改了改
model keras.models.Sequential()
model.add( keras.layers.Conv2D( filters 64, kernel_size(11,11),strides (1,1), paddingvalid, activation tf.keras.activations.relu) )
model.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model.add( keras.layers.Conv2D( filters 192, kernel_size(5,5),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model.add( keras.layers.Conv2D( filters 256, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))model.add( keras.layers.Flatten() )
model.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model.add( keras.layers.Dropout(rate0.5) )
model.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model.add( keras.layers.Dropout(rate0.5) )model.add( keras.layers.Dense(units10 , activation keras.activations.softmax ) )编译和训练模型
在keras中关于交叉熵分类有两个函数sparse_categorical_crossentropy和categorical_crossentropy这里就出现了第一个坑如果将标签[batch_size,10]输入到编译器使用sparse_...的时候回报错
logits and labels must have the same first dimension,got logits shape [200,10] and labels shape [2000]好像是默认把他拉长拼起来了所以我们要使用后者
model.compile( optimizer keras.optimizers.Adam(),loss keras.losses.categorical_crossentropy, metrics[accuracy] )然后就可以训练模型了
model.fit(train_x,train_y,epochs2, batch_size200)Epoch 1/2
60000/60000 [] - 26s 435us/step - loss: 0.2646 - acc: 0.9110
Epoch 2/2
60000/60000 [] - 24s 407us/step - loss: 0.0510 - acc: 0.9855
tensorflow.python.keras.callbacks.History at 0x7f65fe2de940还能看网络结构和参数使用summary()函数
model.summary()_________________________________________________________________
Layer (type) Output Shape Param # conv2d (Conv2D) multiple 7808
_________________________________________________________________
max_pooling2d (MaxPooling2D) multiple 0
_________________________________________________________________
conv2d_1 (Conv2D) multiple 307392
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 multiple 0
_________________________________________________________________
conv2d_2 (Conv2D) multiple 663936
_________________________________________________________________
conv2d_3 (Conv2D) multiple 1327488
_________________________________________________________________
conv2d_4 (Conv2D) multiple 884992
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 multiple 0
_________________________________________________________________
flatten (Flatten) multiple 0
_________________________________________________________________
dense (Dense) multiple 4198400
_________________________________________________________________
dropout (Dropout) multiple 0
_________________________________________________________________
dense_1 (Dense) multiple 16781312
_________________________________________________________________
dropout_1 (Dropout) multiple 0
_________________________________________________________________
dense_2 (Dense) multiple 40970 Total params: 24,212,298
Trainable params: 24,212,298
Non-trainable params: 0
_________________________________________________________________可以用测试集评估模型
print(test_x.shape, test_y.shape)
model.evaluate( test_x ,test_y)(10000, 28, 28, 1) (10000, 10)
10000/10000 [] - 3s 283us/step
[0.03784323987539392, 0.9897]还能预测单张图片,但是要注意输入的第一个维度是样本数, 记得增加一个维度
test_img_idx 1000
test_img test_x[test_img_idx,...]
test_img test_img[np.newaxis,...]
img_prob model.predict( test_img )plt.figure()
plt.imshow( np.squeeze(test_img) )
plt.title(img_prob.argmax())保存模型
训练过程中保存检查点
函数为keras.callbacks.ModelCheckpoint
checkpoint_path./train_save/mnist.ckpt
checkpoint_dir os.path.dirname(checkpoint_path)
# 创建检查回调点
cp_callback keras.callbacks.ModelCheckpoint( checkpoint_path, save_weights_only True, verbose1 )model.fit(train_x, train_y,epochs2, validation_data(test_x,test_y), callbacks[cp_callback] )Train on 60000 samples, validate on 10000 samples
Epoch 1/2
59968/60000 [.] - ETA: 0s - loss: 0.1442 - acc: 0.9681
Epoch 00001: saving model to ./train_save/mnist.ckpt
WARNING:tensorflow:This model was compiled with a Keras optimizer (tensorflow.python.keras.optimizers.Adam object at 0x7faff48fae80) but is being saved in TensorFlow format with save_weights. The models weights will be saved, but unlike with TensorFlow optimizers in the TensorFlow format the optimizers state will not be saved.Consider using a TensorFlow optimizer from tf.train.
60000/60000 [] - 93s 2ms/step - loss: 0.1442 - acc: 0.9681 - val_loss: 0.0693 - val_acc: 0.9811
Epoch 2/2
59968/60000 [.] - ETA: 0s - loss: 0.0757 - acc: 0.9840
Epoch 00002: saving model to ./train_save/mnist.ckpt
WARNING:tensorflow:This model was compiled with a Keras optimizer (tensorflow.python.keras.optimizers.Adam object at 0x7faff48fae80) but is being saved in TensorFlow format with save_weights. The models weights will be saved, but unlike with TensorFlow optimizers in the TensorFlow format the optimizers state will not be saved.Consider using a TensorFlow optimizer from tf.train.
60000/60000 [] - 92s 2ms/step - loss: 0.0757 - acc: 0.9839 - val_loss: 0.0489 - val_acc: 0.9876
tensorflow.python.keras.callbacks.History at 0x7fafead25f98发现有个warnning意思是说模型使用的是keras的优化器保存以后不是tensorflow能直接使用的模型格式好像少了个状态需要使用tensorflow自带的优化器好吧调整代码
import os
model.compile(optimizer tf.train.AdamOptimizer(),loss keras.losses.categorical_crossentropy, metrics[accuracy] )checkpoint_path./train_save2/mnist.ckpt
checkpoint_dir os.path.dirname(checkpoint_path)
# 创建检查回调点
cp_callback keras.callbacks.ModelCheckpoint( checkpoint_path, save_weights_only True, verbose1 )model.fit(train_x, train_y,epochs2, validation_data(test_x,test_y), callbacks[cp_callback] )Train on 60000 samples, validate on 10000 samples
Epoch 1/2
59936/60000 [.] - ETA: 0s - loss: 0.2241 - acc: 0.9325
Epoch 00001: saving model to ./train_save2/mnist.ckpt
60000/60000 [] - 60s 1ms/step - loss: 0.2239 - acc: 0.9326 - val_loss: 0.1009 - val_acc: 0.9765
Epoch 2/2
59936/60000 [.] - ETA: 0s - loss: 0.0866 - acc: 0.9801
Epoch 00002: saving model to ./train_save2/mnist.ckpt
60000/60000 [] - 56s 930us/step - loss: 0.0867 - acc: 0.9800 - val_loss: 0.0591 - val_acc: 0.9855
tensorflow.python.keras.callbacks.History at 0x7fad1a90d7b8这回没出错了尝试构建一个没训练的模型将参数载入进来
model_test keras.models.Sequential()
model_test.add( keras.layers.Conv2D( filters 64, kernel_size(11,11),strides (1,1), paddingvalid, activation tf.keras.activations.relu) )
model_test.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test.add( keras.layers.Conv2D( filters 192, kernel_size(5,5),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test.add( keras.layers.Conv2D( filters 256, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))model_test.add( keras.layers.Flatten() )
model_test.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test.add( keras.layers.Dropout(rate0.5) )
model_test.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test.add( keras.layers.Dropout(rate0.5) )model_test.add( keras.layers.Dense(units10 , activation keras.activations.softmax ) )model_test.compile(optimizer tf.train.RMSPropOptimizer(learning_rate0.01),loss keras.losses.categorical_crossentropy, metrics[accuracy] )载入最近的检查点
! ls train_save
latest tf.train.latest_checkpoint(train_save2)#checkpoint mnist.ckpt.data-00000-of-00001 mnist.ckpt.index
type(latest)#str
loss,acc model_test.evaluate(test_x,test_y)
print(未载入权重时:准确率{:5.2f}%.format(100*acc))
model_test.load_weights(latest)
loss,acc model_test.evaluate(test_x,test_y)
print(载入权重时:准确率{:5.2f}%.format(100*acc))10000/10000 [] - 3s 308us/step
未载入权重时:准确率 9.60%
10000/10000 [] - 3s 264us/step
载入权重时:准确率98.60%间隔保存
也可以指定多少次训练保存一次检查点这样能够有效防止过拟合以后自己可以挑选比较好的训练参数
checkpoint_pathtrain_save3/cp-{epoch:04d}.ckpt
checkpoint_dir os.path.dirname(checkpoint_path)
cp_callback keras.callbacks.ModelCheckpoint(checkpoint_path,verbose1, save_weights_onlyTrue, period1)
model.fit(train_x,train_y,epochs2, callbacks[cp_callback], validation_data[test_x,test_y],verbose1)Train on 60000 samples, validate on 10000 samples
Epoch 1/2
59936/60000 [.] - ETA: 0s - loss: 0.0447 - acc: 0.9897
Epoch 00001: saving model to train_save3/cp-0001.ckpt
60000/60000 [] - 61s 1ms/step - loss: 0.0446 - acc: 0.9897 - val_loss: 0.0421 - val_acc: 0.9920
Epoch 2/2
59936/60000 [.] - ETA: 0s - loss: 0.0478 - acc: 0.9885
Epoch 00002: saving model to train_save3/cp-0002.ckpt
60000/60000 [] - 61s 1ms/step - loss: 0.0478 - acc: 0.9884 - val_loss: 0.0590 - val_acc: 0.9859
tensorflow.python.keras.callbacks.History at 0x7fafea497dd8重新构建一个未训练的模型调用第一次的训练结果
model_test1 keras.models.Sequential()
model_test1.add( keras.layers.Conv2D( filters 64, kernel_size(11,11),strides (1,1), paddingvalid, activation tf.keras.activations.relu) )
model_test1.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test1.add( keras.layers.Conv2D( filters 192, kernel_size(5,5),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test1.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test1.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test1.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test1.add( keras.layers.Conv2D( filters 256, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test1.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))model_test1.add( keras.layers.Flatten() )
model_test1.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test1.add( keras.layers.Dropout(rate0.5) )
model_test1.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test1.add( keras.layers.Dropout(rate0.5) )model_test1.add( keras.layers.Dense(units10 , activation keras.activations.softmax ) )model_test1.compile(optimizer tf.train.AdamOptimizer(learning_rate0.01),loss keras.losses.categorical_crossentropy, metrics[accuracy] )选择第一个检查点载入
loss,accmodel_test1.evaluate(test_x,test_y)
print(未载入权重时:准确率{:5.2f}%.format(100*acc))
model_test1.load_weights(train_save3/cp-0001.ckpt)
loss,accmodel_test1.evaluate(test_x,test_y)
print(载入权重时:准确率{:5.2f}%.format(100*acc))10000/10000 [] - 3s 260us/step
未载入权重时:准确率10.28%
10000/10000 [] - 2s 244us/step
载入权重时:准确率98.30%手动保存模型
在训练完毕以后也可以自行调用save_weights函数保存权重
model.save_weights(./train_save3/mnist_checkpoint)构建未训练模型
model_test2 keras.models.Sequential()
model_test2.add( keras.layers.Conv2D( filters 64, kernel_size(11,11),strides (1,1), paddingvalid, activation tf.keras.activations.relu) )
model_test2.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test2.add( keras.layers.Conv2D( filters 192, kernel_size(5,5),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test2.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test2.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test2.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test2.add( keras.layers.Conv2D( filters 256, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test2.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))model_test2.add( keras.layers.Flatten() )
model_test2.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test2.add( keras.layers.Dropout(rate0.5) )
model_test2.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test2.add( keras.layers.Dropout(rate0.5) )model_test2.add( keras.layers.Dense(units10 , activation keras.activations.softmax ) )model_test2.compile(optimizer tf.train.AdamOptimizer(learning_rate0.01),loss keras.losses.categorical_crossentropy, metrics[accuracy] )读取权重以及评估模型
loss,acc model_test2.evaluate(test_x,test_y)
print(未载入权重时:准确率{:5.2f}%.format(100*acc))
model_test2.load_weights(./train_save3/mnist_checkpoint)
loss,acc model_test2.evaluate(test_x,test_y)
print(载入权重时:准确率{:5.2f}%.format(100*acc))10000/10000 [] - 3s 303us/step
未载入权重时:准确率12.15%
10000/10000 [] - 3s 260us/step
载入权重时:准确率98.59%全部保存
同时保存模型与参数 构建未训练模型
model_test3 keras.models.Sequential()
model_test3.add( keras.layers.Conv2D( filters 64, kernel_size(11,11),strides (1,1), paddingvalid, activation tf.keras.activations.relu) )
model_test3.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test3.add( keras.layers.Conv2D( filters 192, kernel_size(5,5),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test3.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test3.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test3.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test3.add( keras.layers.Conv2D( filters 256, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test3.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))model_test3.add( keras.layers.Flatten() )
model_test3.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test3.add( keras.layers.Dropout(rate0.5) )
model_test3.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test3.add( keras.layers.Dropout(rate0.5) )model_test3.add( keras.layers.Dense(units10 , activation keras.activations.softmax ) )model_test3.compile(optimizer tf.train.AdamOptimizer(),loss keras.losses.categorical_crossentropy, metrics[accuracy] )
model_test3.fit(train_x,train_y,batch_size200,epochs2)保存
model_test3.save(my_model.h5)Currently save requires model to be a graph network. Consider using save_weights, in order to save the weights of the model.出现错误意思是需要定义的模型是一个图网络结构只能保存权重。其实错误原因在于我们的第一层没有定义输入的大小尝试定义一波
model_test4 keras.models.Sequential()
model_test4.add( keras.layers.Conv2D( filters 64, kernel_size(11,11),strides (1,1), paddingvalid, activation tf.keras.activations.relu,input_shape(28,28,1)) )
model_test4.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test4.add( keras.layers.Conv2D( filters 192, kernel_size(5,5),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test4.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test4.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test4.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test4.add( keras.layers.Conv2D( filters 256, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test4.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))model_test4.add( keras.layers.Flatten() )
model_test4.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test4.add( keras.layers.Dropout(rate0.5) )
model_test4.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test4.add( keras.layers.Dropout(rate0.5) )model_test4.add( keras.layers.Dense(units10 , activation keras.activations.softmax ) )model_test4.compile(optimizer tf.train.AdamOptimizer(),loss keras.losses.categorical_crossentropy, metrics[accuracy] )
model_test4.fit(train_x,train_y,batch_size200,epochs2)Epoch 1/2
60000/60000 [] - 22s 364us/step - loss: 0.4112 - acc: 0.8556
Epoch 2/2
60000/60000 [] - 21s 342us/step - loss: 0.0584 - acc: 0.9838
tensorflow.python.keras.callbacks.History at 0x7f137972f4a8尝试保存
model_test4.save(my_model.h5)WARNING:tensorflow:TensorFlow optimizers do not make it possible to access optimizer attributes or optimizer state after instantiation. As a result, we cannot save the optimizer as part of the model save file.You will have to compile your model again after loading it. Prefer using a Keras optimizer instead (see keras.io/optimizers).又出warning说是不能使用tensorflow的优化器要使用keras自带的优化器好吧改
model_test5 keras.models.Sequential()
model_test5.add( keras.layers.Conv2D( filters 64, kernel_size(11,11),strides (1,1), paddingvalid, activation tf.keras.activations.relu,input_shape(28,28,1)) )
model_test5.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test5.add( keras.layers.Conv2D( filters 192, kernel_size(5,5),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test5.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))
model_test5.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test5.add( keras.layers.Conv2D( filters 384, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test5.add( keras.layers.Conv2D( filters 256, kernel_size(3,3),strides (1,1), paddingsame, activation tf.keras.activations.relu) )
model_test5.add( keras.layers.MaxPool2D( pool_size(2,2),strides(2,2) ))model_test5.add( keras.layers.Flatten() )
model_test5.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test5.add( keras.layers.Dropout(rate0.5) )
model_test5.add( keras.layers.Dense( units4096, activation keras.activations.relu ) )
model_test5.add( keras.layers.Dropout(rate0.5) )model_test5.add( keras.layers.Dense(units10 , activation keras.activations.softmax ) )model_test5.compile(optimizer tf.keras.optimizers.Adam(),loss keras.losses.categorical_crossentropy, metrics[accuracy] )
model_test5.fit(train_x,train_y,batch_size200,epochs2)
model_test5.save(my_model2.h5)Epoch 1/2
60000/60000 [] - 26s 434us/step - loss: 0.2850 - acc: 0.9043
Epoch 2/2
60000/60000 [] - 25s 409us/step - loss: 0.0555 - acc: 0.9847
tensorflow.python.keras.callbacks.History at 0x7f661033a9e8这样就不出错了尝试调用模型和参数因为保存了模型结构和参数所以不需要重新定义网络结构
model_test6 keras.models.load_model(my_model2.h5)
model_test6.summary()_________________________________________________________________
Layer (type) Output Shape Param # conv2d_10 (Conv2D) (None, 18, 18, 64) 7808
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 9, 9, 64) 0
_________________________________________________________________
conv2d_11 (Conv2D) (None, 9, 9, 192) 307392
_________________________________________________________________
max_pooling2d_7 (MaxPooling2 (None, 4, 4, 192) 0
_________________________________________________________________
conv2d_12 (Conv2D) (None, 4, 4, 384) 663936
_________________________________________________________________
conv2d_13 (Conv2D) (None, 4, 4, 384) 1327488
_________________________________________________________________
conv2d_14 (Conv2D) (None, 4, 4, 256) 884992
_________________________________________________________________
max_pooling2d_8 (MaxPooling2 (None, 2, 2, 256) 0
_________________________________________________________________
flatten_2 (Flatten) (None, 1024) 0
_________________________________________________________________
dense_6 (Dense) (None, 4096) 4198400
_________________________________________________________________
dropout_4 (Dropout) (None, 4096) 0
_________________________________________________________________
dense_7 (Dense) (None, 4096) 16781312
_________________________________________________________________
dropout_5 (Dropout) (None, 4096) 0
_________________________________________________________________
dense_8 (Dense) (None, 10) 40970 Total params: 24,212,298
Trainable params: 24,212,298
Non-trainable params: 0
_________________________________________________________________稳如狗做一下测试
测试集上的测试
model_test6.evaluate(test_x,test_y)10000/10000 [] - 3s 302us/step
[0.05095283883444499, 0.9868]单张图片的测试
test_img test_x[5000,...]
test_imgtest_img[ np.newaxis,...]
pred_label model_test6.predict_classes(test_img)
plt.figure()
plt.imshow( np.squeeze(test_img))
plt.title(pred_label)后记
这一章主要学习了如何搭建简单的卷积网络以及集中保存方法仅权重以及权重和模型结构。 主要记住的就是如果仅保存权重注意用tensorflow自带的优化器而保存网络和权重的时候要用keras的优化器 下一章针对深度学习的几个理论做一下理解以及实验包括BatchNorm、ResNet等。 博客代码链接戳这里
