哪个网站做化妆品效果好,品牌策划书范文,如何建立公司网站南通,沈阳正规的男科医院之前一段时间里#xff0c;学习过tensorflow和Pytorch也写了点心得#xff0c;目前是因为项目原因用了一段时间Keras#xff0c;觉得很不错啊#xff0c;至少从入门来说对新手极度友好#xff0c;由于keras是基于tensoflow的基础#xff0c;相当于tensorflow的高级API吧学习过tensorflow和Pytorch也写了点心得目前是因为项目原因用了一段时间Keras觉得很不错啊至少从入门来说对新手极度友好由于keras是基于tensoflow的基础相当于tensorflow的高级API吧如果理解有错可以在下方评论纠正博主哈
一、安装
安装很简单也是基于tensorflow的前提下(如果有疑问请参考博主之前的博客)
pip install keras
二、应用示例
# -*- coding: utf-8 -*-
#
# #在线下载
# from keras.datasets import mnist
# (X_train,Y_train),(X_test,Y_test) mnist.load_data()
#
# print(train:%d imgs%len(X_train))
# print(test:%d imgs%len(X_test))
#
online_or_not False
#本地读取
from tensorflow.examples.tutorials.mnist import input_data
import numpy as npimport matplotlib.pyplot as plt
from PIL import Imagedef show_mnist(train_image,train_labels):n 3m 3for i in range(n):for j in range(m):plt.subplot(n,m,i*nj1)#plt.subplots_adjust(wspace0.2, hspace0.8)index i * n j #当前图片的标号img_array train_image[index]*255img Image.fromarray(img_array)plt.title(train_labels[index])plt.imshow(img,cmapGreys)plt.show()#show_mnist(x_train, y_train)# coding: utf-8
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense, Activation, Convolution2D, MaxPooling2D, Flatten
from keras.optimizers import Adam
np.random.seed(1337)mnist数据集的label本身进行了one-hot标签化处理
if online_or_not:# download the mnist(X_train, Y_train), (X_test, Y_test) mnist.load_data()# data pre-processingX_train X_train.reshape(-1, 1, 28, 28)/255X_test X_test.reshape(-1, 1, 28, 28)/255Y_train np_utils.to_categorical(Y_train, num_classes10)Y_test np_utils.to_categorical(Y_test, num_classes10)
else:X_train []X_test []print(train:%d imgs%len(X_train))
print(test:%d imgs%len(X_test))# build CNN
model Sequential()# conv layer 1 output shape(32, 28, 28)
model.add(Convolution2D(filters32,kernel_size5,strides1,paddingsame,batch_input_shape(None, 1, 28, 28),data_formatchannels_first))
model.add(Activation(relu))# pooling layer1 (max pooling) output shape(32, 14, 14)
model.add(MaxPooling2D(pool_size2, strides2, paddingsame, data_formatchannels_first))# conv layer 2 output shape (64, 14, 14)
model.add(Convolution2D(64, 5, strides1, paddingsame, data_formatchannels_first))
model.add(Activation(relu))# pooling layer 2 (max pooling) output shape (64, 7, 7)
model.add(MaxPooling2D(2, 2, same, data_formatchannels_first))# full connected layer 1 input shape (64*7*73136), output shape (1024)
model.add(Flatten())
model.add(Dense(1024))
model.add(Activation(relu))# full connected layer 2 to shape (10) for 10 classes
model.add(Dense(10))
model.add(Activation(softmax))model.summary()
# define optimizer
adam Adam(lr1e-4)
model.compile(optimizeradam, losscategorical_crossentropy, metrics[accuracy])# training
print (Training)
model.fit(X_train, Y_train, epochs1, batch_size128)# testing
print (Testing)
loss, accuracy model.evaluate(X_test, Y_test)
print (loss, accuracy: , (loss, accuracy))
三、模型可视化
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense, Activation, Convolution2D, MaxPooling2D, Flatten
from keras.optimizers import Adam
#模型可视化引入
import keras.callbacks
import tensorflow as tf
np.random.seed(1337)(X_train, Y_train), (X_test, Y_test) mnist.load_data()# data pre-processing
X_train X_train.reshape(-1, 1, 28, 28)/255
X_test X_test.reshape(-1, 1, 28, 28)/255
Y_train np_utils.to_categorical(Y_train, num_classes10)
Y_test np_utils.to_categorical(Y_test, num_classes10)# build CNN
def build_model():model Sequential()# conv layer 1 output shape(32, 28, 28)model.add(Convolution2D(filters32,kernel_size5,strides1,paddingsame,batch_input_shape(None, 1, 28, 28),data_formatchannels_first))model.add(Activation(relu))# pooling layer1 (max pooling) output shape(32, 14, 14)model.add(MaxPooling2D(pool_size2, strides2, paddingsame, data_formatchannels_first))# conv layer 2 output shape (64, 14, 14)model.add(Convolution2D(64, 5, strides1, paddingsame, data_formatchannels_first))model.add(Activation(relu))# pooling layer 2 (max pooling) output shape (64, 7, 7)model.add(MaxPooling2D(2, 2, same, data_formatchannels_first))# full connected layer 1 input shape (64*7*73136), output shape (1024)model.add(Flatten())model.add(Dense(1024))model.add(Activation(relu))# full connected layer 2 to shape (10) for 10 classesmodel.add(Dense(10))model.add(Activation(softmax))model.summary()return model
model build_model()
# define optimizer
adam Adam(lr1e-4)
model.compile(optimizeradam, losscategorical_crossentropy, metrics[accuracy])#模型可视化
tb_config keras.callbacks.TensorBoard(log_dir E:/python/kerascode/mnist_cnn/logs, write_images 1, histogram_freq 0)
cbks [tb_config]# training
print (Training)
#模型可视化需要加入“callbacks cbks”
model.fit(X_train, Y_train, epochs1, callbacks cbks, batch_size512)# testing
print (Testing)
loss, accuracy model.evaluate(X_test, Y_test)
print (loss, accuracy: , (loss, accuracy))
会在 log_dir E:/python/kerascode/mnist_cnn/logs该文件夹处生成events.out.tfevents.1566199816.ZD 训练日志打开Anaconda Prompt激活对应的环境定位到logs文件的上一级目录如下图所示输入
tensorboard --logdirAB
此处AB即上文中的logs文件夹名称。 将网址复制到谷歌浏览器中即可结果如下图所示 四、模型可视化踩坑
from keras.utils.vis_utils import plot_model
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.layers.embeddings import Embedding
from keras.layers.recurrent import LSTMmodel Sequential()
model.add(Embedding(input_dim1024, output_dim256, input_length50))
model.add(LSTM(128)) # try using a GRU instead, for fun
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation(sigmoid))plot_model(model, to_filemodel1.png, show_shapesTrue)
这个过程会报错
raise ImportError(Failed to import pydot. Please install pydot. For example with pip install pydot.)
作为一个菜鸡只能查到是导入pydot发生错误很尴尬还好有个博客大佬教会如何改错。
打开vis_utils.py文件将相应地方注释并加入下列代码
# pydot is an optional dependency,
# see extras_require in setup.py.
#
# try:
# import pydot
# except ImportError:
# pydot None
#
try:import pydot_ng as pydot
except ImportError:try:import pydotplus as pydotexcept ImportError:try:import pydotexcept ImportError:pydotNone
参考文献
https://blog.csdn.net/xu_haim/article/details/84981284
