【keras】用tensorboard监视CNN每一层的输出
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.layers import Conv1D, MaxPooling1D
import scipy.io as sio
import matplotlib.pyplot as plt
from keras.utils import np_utils
import keras
import numpy as np
from keras import regularizers
from keras.callbacks import TensorBoard
from keras.utils import plot_model
from keras import backend as K
from os.path import exists, join from os import makedirs batch_sizes = 256
nb_class = 10
nb_epochs = 2
log_dir = './bgbv2_log_dir' if not exists(log_dir):
makedirs(log_dir) # input image dimensions
img_rows, img_cols = 1, 2048
'''
第一步 准备数据
'''
# matlab文件名 准备数据
file_name = u'G:/GANCode/CSWU/12k drive end vps/trainset/D/D_dataset.mat'
original_data = sio.loadmat(file_name)
X_train = original_data['x_train']
Y_train = original_data['y_train']
X_test = original_data['x_test']
Y_test = original_data['y_test']
channel = 1 X_train = X_train.reshape((X_train.shape[0], X_train.shape[1], channel))
X_test = X_test.reshape((X_test.shape[0], X_test.shape[1], channel))
input_shape = (X_train.shape[1], channel) # 标签打乱
permutation = np.random.permutation(Y_train.shape[0])
X_train = X_train[permutation, :, :]
Y_train = Y_train[permutation] permutation = np.random.permutation(Y_test.shape[0])
X_test = X_test[permutation, :, :]
Y_test = Y_test[permutation] X_train = X_train.astype('float32') # astype SET AS TYPE INTO
X_test = X_test.astype('float32')
#X_train = (X_train+1)/2
#X_test = (X_test+1)/2
print('x_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples') X_meta = X_test.reshape((X_test.shape[0], X_test.shape[1])) kkkkk=0 # save class labels to disk to color data points in TensorBoard accordingly
with open(join(log_dir, 'metadata.tsv'), 'w') as f:
np.savetxt(f, Y_test[:200]) '''
第三步 设置标签 one-hot
'''
Y_test = np_utils.to_categorical(Y_test, nb_class) # Label
Y_train = np_utils.to_categorical(Y_train, nb_class) '''
第四步 网络model
'''
model = Sequential()
model.add(Conv1D(64, 11, activation='relu', input_shape=(2048, 1)))
model.add(Conv1D(64, 11, activation='relu'))
model.add(MaxPooling1D(3))
model.add(Conv1D(128, 11, activation='relu'))
model.add(Conv1D(128, 11, activation='relu')) '''
model.add(GlobalAveragePooling1D())
model.add(Dropout(0.5)) '''
model.add(MaxPooling1D(3))
model.add(Dropout(0.25))
model.add(keras.layers.Flatten())
model.add(Dense(1000, activation='relu'))
model.add(Dense(100, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax')) embedding_layer_names = set(layer.name
for layer in model.layers
if layer.name.startswith('dense_')) # https://stackoverflow.com/questions/45265436/keras-save-image-embedding-of-the-mnist-data-set model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy']) callbacks = [keras.callbacks.TensorBoard(
log_dir='bgbv2_log_dir',
embeddings_layer_names=['dense_2'], #监视某一层,就要写某一层的名字,可以同时监视很多层,用上面的字典形式。
#embeddings_metadata='metadata.tsv',
embeddings_freq=1,
#histogram_freq=1,
embeddings_data=X_test # 数据要和X_train保持一致。这里我用的是一维数据,(60000,2048,1)表示有6万个样本,每个样本有2048个长度,且每个样本有1个通道(1个传感器),换成多个通道的话,就要使用多个传感器的数据。
)] model.fit(X_train, Y_train,
batch_size=batch_sizes,
callbacks=callbacks,
epochs=nb_epochs,
verbose=1,
validation_data=(X_test, Y_test)) xxasfs=1
# You can now launch tensorboard with `tensorboard --logdir=./logs` on your
# command line and then go to http://localhost:6006/#projector to view the
# embeddings
# keras.callbacks.TensorBoard(
# log_dir='./logs',
# histogram_freq=0,
# batch_size=32,
# write_graph=True,
# write_grads=False,
# write_images=False,
# embeddings_freq=0,
# embeddings_layer_names=None,
# embeddings_metadata=None,
# embeddings_data=None,
# update_freq='epoch')
坑死我了。
没有人教,自己琢磨了一天。
下面就能清楚地看见我们的三维图啦~用来写paper和PPT都是极好的素材。
PS:任何一个图层的输出:
https://stackoverflow.com/questions/41711190/keras-how-to-get-the-output-of-each-layer
参考1,keras Tensorboard官方说明
https://keras.io/callbacks/#tensorboard
from __future__ import print_function from os import makedirs
from os.path import exists, join import keras
from keras.callbacks import TensorBoard
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K import numpy as np batch_size = 128
num_classes = 10
epochs = 12
log_dir = './logs' if not exists(log_dir):
makedirs(log_dir) # input image dimensions
img_rows, img_cols = 28, 28 # the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data() if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1) x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples') # save class labels to disk to color data points in TensorBoard accordingly
with open(join(log_dir, 'metadata.tsv'), 'w') as f:
np.savetxt(f, y_test) # convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes) tensorboard = TensorBoard(batch_size=batch_size,
embeddings_freq=1,
embeddings_layer_names=['features'],
embeddings_metadata='metadata.tsv',
embeddings_data=x_test) model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu', name='features'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax')) model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy']) model.fit(x_train, y_train,
batch_size=batch_size,
callbacks=[tensorboard],
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1]) # You can now launch tensorboard with `tensorboard --logdir=./logs` on your
# command line and then go to http://localhost:6006/#projector to view the
# embeddings
参考2,keras Mnist最后一层可视化。
https://keras.io/examples/tensorboard_embeddings_mnist/
参考3,IMDB影视评论最后一层可是化
import keras
from keras import layers
from keras.datasets import imdb
from keras.preprocessing import sequence
max_features = 500 # 原文为2000
max_len = 500
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
x_train = sequence.pad_sequences(x_train, maxlen=max_len)
x_test = sequence.pad_sequences(x_test, maxlen=max_len) KK=x_train[:100].astype("float32")
MM=1 model = keras.models.Sequential()
model.add(layers.Embedding(max_features, 128, input_length=max_len, name='embed'))
model.add(layers.Conv1D(32, 7, activation='relu'))
model.add(layers.MaxPooling1D(5))
model.add(layers.Conv1D(32, 7, activation='relu'))
model.add(layers.GlobalMaxPooling1D())
model.add(layers.Dense(1))
model.summary()
model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])
callbacks = [keras.callbacks.TensorBoard(
log_dir='my_log_dir',
histogram_freq=1,
embeddings_freq=1,
embeddings_data=x_train[:100].astype("float32")
)]
history = model.fit(x_train, y_train, epochs=20, batch_size=128, validation_split=0.2, callbacks=callbacks) #补充 https://codeday.me/bug/20180924/267508.html
【keras】用tensorboard监视CNN每一层的输出的更多相关文章
- Keras(四)CNN 卷积神经网络 RNN 循环神经网络 原理及实例
CNN 卷积神经网络 卷积 池化 https://www.cnblogs.com/peng8098/p/nlp_16.html 中有介绍 以数据集MNIST构建一个卷积神经网路 from keras. ...
- keras与tensorboard结合使用
使用tensorboard将keras的训练过程显示出来(动态的.直观的)是一个绝好的主意,特别是在有架设好的VPS的基础上,这篇文章就是一起来实现这个过程. 一.主要原理 keras的在训练(fit ...
- 【Keras案例学习】 CNN做手写字符分类(mnist_cnn )
from __future__ import print_function import numpy as np np.random.seed(1337) from keras.datasets im ...
- fasttext和cnn的比较,使用keras imdb看效果——cnn要慢10倍。
fasttext: '''This example demonstrates the use of fasttext for text classification Based on Joulin e ...
- CNN中下一层Feature map大小计算
符号表示: $W$:表示当前层Feature map的大小. $K$:表示kernel的大小. $S$:表示Stride的大小. 具体来讲: 整体说来,和下一层Feature map大小最为密切的就是 ...
- keras启用tensorboard
在callback函数中添加tensorboard,启用tensorboard. # TensorBoard callback tensorboard_cb = K.callbacks.TensorB ...
- Keras框架下使用CNN进行CIFAR-10的识别测试
有手册,然后代码不知道看一下:https://keras-cn.readthedocs.io/en/latest/ 首先是下载数据集,下载太慢了就从网盘上下载: 链接:https://pan.baid ...
- pytorch 中LSTM模型获取最后一层的输出结果,单向或双向
单向LSTM import torch.nn as nn import torch seq_len = 20 batch_size = 64 embedding_dim = 100 num_embed ...
- caffe网络中屏蔽某一层的输出Silence层
屏蔽label输出 layer { name: "silence0" type: "Silence" bottom: "label" pha ...
随机推荐
- css两列布局之基于BFC规则实现
css要实现常见的自适应两列布局的方式方法挺多. 这里讲的是利用设置overflow不为visible时会形成新的BFC来实现.至于什么是BFC,可以搜搜看先,基本都讲的差不多了.等有更多空余时间,专 ...
- 【Hadoop篇】--Hadoop常用命令总结
一.前述 分享一篇hadoop的常用命令的总结,将常用的Hadoop命令总结如下. 二.具体 1.启动hadoop所有进程start-all.sh等价于start-dfs.sh + start-yar ...
- 在Linux(Centos7)上使用Docker运行.NetCore
在上一篇中我们写了如何在windows中使用docker运行.netcore,既然我们了解了windows下的运行发布,我们也可以试试linux下使用docker运行.netcore项目,那么今天我们 ...
- .NET Core微服务之基于Steeltoe使用Zipkin实现分布式追踪
Tip: 此篇已加入.NET Core微服务基础系列文章索引 => Steeltoe目录快速导航: 1. 基于Steeltoe使用Spring Cloud Eureka 2. 基于Steelt ...
- ASP.NET Core中使用GraphQL - 第七章 Mutation
ASP.NET Core中使用GraphQL - 目录 ASP.NET Core中使用GraphQL - 第一章 Hello World ASP.NET Core中使用GraphQL - 第二章 中间 ...
- 关闭 Mac 拼写自动纠正与横线转换
如果你是个程序员, 如果你恰好用 mac 自带的 notes 来做笔记, 很大可能性, 你会在里面贴代码, 但是, Mac 的拼写检查和自动纠正功能,会把代码变成你不想要的样子, 比如, 它会为你首字 ...
- 全文检索-Elasticsearch (三) DSL
DSL:elasticsearch查询语言elasticsearch对json 的语法有严格的要求,每个json串不能换行,同时一个json串和一个json串之间,必须有一个换行 DSL(介绍查询语言 ...
- Visual Studio 2019 正式发布,重磅更新,支持live share
如约而至,微软已于今天推出 Visual Studio 2019 正式版,一同发布的还有 Visual Studio 2019 for Mac. Visual Studio 2019 下载地址:htt ...
- 分布式缓存Hazelcast案例一
分布式缓存Hazelcast案例一 Hazelcast IMDG Architecture 今天先到这儿,希望对您技术领导力, 企业管理,物联网, 系统架构设计与评估,团队管理, 项目管理, 产品管 ...
- Eclipse4JavaEE配置Tomcat运行环境
如果我们想搭一个网站,我们可以使用Eclipse for JavaEE IDE进行开发. 初次使用需要配置网站的运行环境,可以去Apache官网下载Tomcat 8.5或Tomcat 9的版本 然后打 ...