- 博客(62)
- 收藏
- 关注
RSS订阅原创 keras Timedistributed lstm+cnn
# univariate cnn-lstm examplefrom numpy import arrayfrom keras.models import Sequentialfrom keras.layers import LSTMfrom keras.models import Modelfrom keras.layers import Flattenfrom keras.layer...
2018-10-31 13:09:40
3836
1
原创 keras ConvLSTM2D 官方例子
""" This script demonstrates the use of a convolutional LSTM network.This network is used to predict the next frame of an artificiallygenerated movie which contains moving squares."""from keras.mo...
2018-10-30 11:58:18
8785
2
原创 keras +ConvLSTM2D
import numpy as np, scipy.ndimage, matplotlib.pyplot as pltfrom scipy import statsfrom keras.models import Sequentialfrom keras.layers import Dense, Dropout, Activation, Flattenfrom keras.layers i...
2018-10-30 11:37:10
6346
6
原创 CNN Long Short-Term Memory
model = Sequential()# define CNN modelmodel.add(TimeDistributed(Conv2D(...))model.add(TimeDistributed(MaxPooling2D(...)))model.add(TimeDistributed(Flatten()))# define LSTM modelmodel.add(LSTM...
2018-10-29 15:39:01
350
原创 keras cnn+rnn
# univariate cnn-lstm examplefrom numpy import arrayfrom keras.models import Sequentialfrom keras.layers import LSTMfrom keras.layers import Densefrom keras.layers import Flattenfrom keras.layer...
2018-10-29 15:35:49
2271
原创 keras generater
import kerasfrom keras.models import Sequentialfrom keras.layers import Denseimport numpy as npfrom sklearn.model_selection import train_test_splitcount =1 data=np.array([[1, 2, 0, 1], ...
2018-10-29 11:32:18
310
原创 gb
<div class="article-copyright"> 版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u011026329/article/details/79190347 </div> <div class="markdown_vie...
2018-10-28 17:37:10
159
原创 python generater yeild
#listL = [x * x for x in range(10)]#generraterg = (x * x for x in range(10))gOut[4]: <generator object <genexpr> at 0x7f3d143048e0>LOut[5]: [0, 1, 4, 9, 16, 25, 36, 49, 64, 81]...
2018-10-28 11:25:35
483
原创 tf.split()
import numpy as npimport tensorflow as tfa=np.reshape(range(24),(4,2,3))sess=tf.InteractiveSession()b= tf.split(a,1,0)c=sess.run(b)切割cOut[37]: [array([[[ 0, 1, 2], [ 3, 4, 5]]...
2018-10-26 19:18:03
934
原创 tf.transpose()
import tensorflow as tf; import numpy as np; x = tf.constant([[1, 2, 3], [4, 5, 6]])cc=tf.transpose(x)init = tf.initialize_all_variables()sess = tf.Session()sess.run(init) # Very import...
2018-10-26 10:50:36
163
原创 tensorflow 保存模型
#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Thu Oct 25 15:29:59 2018@author: lg"""import tensorflow as tfimport numpy as npimport matplotlib.pyplot as pltmoney=np.ar
2018-10-25 19:27:56
259
原创 tensorflow 双向lstm
#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Thu Oct 25 13:41:35 2018@author: lg"""import numpy as npimport pandas as pdimport tensorflow as tfimport tensorflow.contrib.rnn as...
2018-10-25 19:21:56
2365
原创 tensorflow lstm (一)
import numpy as np import tensorflow as tf import tensorflow.contrib.rnn as rnn import matplotlib.pyplot as plt import matplotlib.pyplot as pltTIME_STEPS=10BATCH_SIZE=128HIDDEN_UNITS1=30HIDDE...
2018-10-25 19:20:21
320
原创 tf.pad()
网上看到很多tf.pad的文章，很多都语焉不详，需自己动手操作才能真正理解，pad,一言以蔽之，就是在矩阵的周围补0。对于二维矩阵，就是在 上 ，下，左，右补0import numpy as npimport tensorflow as tf # 创建一个二维变量,默认执行CONSTANT填充vct = tf.Variable(tf.ones([3, 4]), name=&quot;vct&quot;...
2018-10-23 10:49:30
2238
1
原创 tensorboard 远程
在登录远程服务器的时候使用命令：ssh -L 16006:127.0.0.1:6006 name@server_ipnohup python file_name.py &gt;p1.log &gt;tensorboard --logdir=./log在本机浏览器输入：http://127.0.0.1:16006/...
2018-10-22 14:33:23
290
原创 tensorboard 远程
在登录远程服务器的时候使用命令：ssh -L 16006:127.0.0.1:6006 name@server_ipnohup python file_name.py >p1.log >tensorboard --logdir=./log在本机浏览器输入：http://127.0.0.1:16006/ ...
2018-10-22 14:33:00
67
原创 tensorboard 用法（二）
#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Mon Oct 22 13:04:34 2018@author: lg"""#!/usr/bin/env python3# -*- coding: utf-8 -*-import tensorflow as tfimport matp
2018-10-22 14:27:26
139
原创 tensorboard 用法（二）
#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Mon Oct 22 13:04:34 2018@author: lg"""#!/usr/bin/env python3# -*- coding: utf-8 -*-import tensorflow...
2018-10-22 14:27:00
72
原创 tensorboard 用法（一）
import tensorflow as tfimport numpy as np## prepare the original datawith tf.name_scope('data'): x_data = np.random.rand(100).astype(np.float32) y_data = 0.3*x_data+0.1##creat parameter...
2018-10-22 14:26:04
316
原创 tensorboard 用法（一）
import tensorflow as tfimport numpy as np## prepare the original datawith tf.name_scope('data'): x_data = np.random.rand(100).astype(np.float32) y_data = 0.3...
2018-10-22 14:26:00
67
原创 内省之手机自我管理
手机上有太多低级的东西，会使人愚蠢低效。这是我自己给自己定的法律必须执行工作的时候，手机放在抽屉里睡觉的前后手机放在包里闲的时候不玩手机多看书...
2018-10-20 09:18:19
736
原创 内省之手机自我管理
手机上有太多低级的东西，会使人愚蠢低效。这是我自己给自己定的法律必须执行 1. 工作的时候，手机放在抽屉里2. 睡觉的前后手机放在包里3. 闲的时候不玩手机多看书4.上网时候不要被某条信息的影响，忘记你为什么上网http://www.aqd111.com/videos/play/744 ...
2018-10-20 09:18:00
209
原创 凯利公式判定持仓比例
from matplotlib import pyplot as plt import numpy as np from mpl_toolkits.mplot3d import Axes3D#p是你的胜率#b是你的赔率def caly(p,b): f=(p*(b+1)-1)/b return round...
2018-10-19 17:26:00
232
原创 凯利公式判定持仓比例
from matplotlib import pyplot as plt import numpy as np from mpl_toolkits.mplot3d import Axes3D#p是你的胜率#b是你的赔率def caly(p,b): f=(p*(b+1)-1)/b return round(f,2) 如果你的选股正确率是0.8,赔率是1...
2018-10-19 17:25:59
2621
原创 keras train_on_batch
import numpy as npimport tensorflow as tffrom keras.callbacks import TensorBoardfrom keras.layers import Input, Densefrom keras.models import Modeldef write_log(callback, names, logs, batch_no)...
2018-10-18 18:26:18
14810
1
原创 keras train_on_batch
import numpy as npimport tensorflow as tffrom keras.callbacks import TensorBoardfrom keras.layers import Input, Densefrom keras.models import Modeldef write_log(cal...
2018-10-18 18:26:00
254
2
原创 使用 keras 训练大规模数据
参考1参考2train_on_batchn_epoch = 12batch_size = 16for e in range(n_epoch): print("epoch", e) batch_num = 0 loss_sum=np.array([0.0,0.0]) for X_train, y_t...
2018-10-18 18:16:00
132
原创 keras 时间序列分析
多层感知机#Lesson 03: MLP for Time Series Forecasting# univariate mlp examplefrom numpy import arrayfrom keras.models import Sequentialfrom keras.layers import Dense# def...
2018-10-17 19:15:00
256
原创 keras 时间序列分析
多层感知机#Lesson 03: MLP for Time Series Forecasting# univariate mlp examplefrom numpy import arrayfrom keras.models import Sequentialfrom keras.layers import Dense# define datasetX = array([[10, 2...
2018-10-17 19:14:52
958
原创 完全卸载mongodb
sudo apt-get purge mongodb或者sudo apt-get purge --auto-remove mongodb
2018-10-16 18:08:16
20399
1
原创 keras lstm softmax 多对多
# multinput and multioutput from numpy import arrayfrom keras.models import Sequentialfrom keras.layers import Densefrom keras.layers import TimeDistributedfrom keras.layers import LSTMimport n...
2018-10-16 18:07:39
2319
2
原创 外出就餐
1. 不去路边垃圾小店，聚类算法，多去那种地方，身上将具那些人的特征，不去茅台路面馆， 2. 外出就餐简单最好，牛奶面包就好 3. 在公司，牛奶，面包，水果就好，路边小店多为低端小店，脏乱差...
2018-10-16 13:07:15
1112
原创 TimeDistributed in LSTM
一对一的LSTM# one input and one outputfrom numpy import arrayfrom keras.models import Sequentialfrom keras.layers import Densefrom keras.layers import LSTM# prepare sequencelength = 5seq = array([...
2018-10-13 14:23:04
832
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人