Very very simple example of TensorFlow conv1d. 

import tensorflow as tf
import numpy as np

X = np.zeros((10,10)) + 1
filter = np.zeros((5,),dtype=np.float32) + 1

x = tf.placeholder(tf.float32, shape=[None, 10, 1])
f = tf.placeholder(tf.float32, shape = [5, 1, 1])

conv = tf.nn.conv1d(x, f, 1,'SAME')

session = tf.Session()
result = session.run(conv, feed_dict={x:X.reshape((10,10,1)), f:filter.reshape((5,1,1))})
result.reshape((10,10))

result

array([[ 3.,  4.,  5.,  5.,  5.,  5.,  5.,  5.,  4.,  3.],
       [ 3.,  4.,  5.,  5.,  5.,  5.,  5.,  5.,  4.,  3.],
       [ 3.,  4.,  5.,  5.,  5.,  5.,  5.,  5.,  4.,  3.],
       [ 3.,  4.,  5.,  5.,  5.,  5.,  5.,  5.,  4.,  3.],
       [ 3.,  4.,  5.,  5.,  5.,  5.,  5.,  5.,  4.,  3.],
       [ 3.,  4.,  5.,  5.,  5.,  5.,  5.,  5.,  4.,  3.],
       [ 3.,  4.,  5.,  5.,  5.,  5.,  5.,  5.,  4.,  3.],
       [ 3.,  4.,  5.,  5.,  5.,  5.,  5.,  5.,  4.,  3.],
       [ 3.,  4.,  5.,  5.,  5.,  5.,  5.,  5.,  4.,  3.],
       [ 3.,  4.,  5.,  5.,  5.,  5.,  5.,  5.,  4.,  3.]], dtype=float32)
You need to change 10x10 input to 10x10x1 array. (last 1 is for channel, and I only have one channel.)
Also 5 linear filter to 5x1x1 array. (middle 1 for input channel and last 1 for output channel.)

Comments

Post a Comment

Popular posts from this blog

Calling OpenCV functions via Cython from Python 3.X.

I have managed to run OpenCV function from Python3 via Cython today, so I want to write about it. Before you start something like this, you should know you have to read at least header files of C library to write right definition in Cython,because Cython does not do that for you. I am using virtualenv, python from pythonz, and home-brewed OpenCV. Almost everything of C++ works just fine with Cython, but still, you should do some Voodoo things like for integer template argument. ctypedef void* int_parameter ctypedef int_parameter two "2" ctypedef Point_[float, two] Point2f Now, main sample Cython code is following. #===== testopencv.pyx ======== import numpy as np cimport numpy as np # for np.ndarray from libcpp.string cimport string from libc.string cimport memcpy cdef extern from "opencv2/core/core.hpp": cdef int CV_WINDOW_AUTOSIZE cdef int CV_8UC3 cdef extern from "opencv2/core/core.hpp" namespace "cv": cdef cppclass Mat: Ma...
Read more

Showing CPU/Memory usage on tmux status bar(tmuxのステータスバーにCPUとMemoryの使用状況を表示する)

Image
On OSX, to show CPU usage, script is like this. #!/bin/bash top -l 1 | head -n 4 | tail -n 1|awk '{printf "%3d%%\n", $3}' to get Memory Usage, script is like this. #!/bin/bash vm_stat | awk 'BEGIN{FS="[:]+"}{if(NR<7&&NR>1)sum+=$2; if(NR==2||NR==4||NR==5)free+=$2} END{printf "%3d%%\n",100*((sum - free)/sum)}' Name thsese scripts like getCpuUsage.sh/getMemUsage.sh and put them in folder where the $PATH is set. Change their mode to u+x. To show them on tmux status line, .tmux.conf is like set -g status-right '#[fg=blue,bold]#H#[default] #[fg=blue,bold][CPU=#(getCpuUsage.sh) MEM=#(getMemUsage.sh)]#[default]'
Read more

When "sam local start-api" does not mount public folder as "/"...

With aws-sam-cli, I've been experiencing public folder is not mounted as root(/). For example, if we have ./public/index.html file, it should be accessed as "http://localhost:3000/index.html" after  # sam local start-api (You doesn't have to have -s or --static-dir option if public  folder is OK for you) To make it work  Make sure you have the public folder. confirm  Following message on the screen, "Mounting static files from /api/sam-app/public at /" If the message doesn't show even though you have a public folder (which was my case), try remove . aws-sam/build folder. At least it worked for my case. .aws-sam/build is recreated every time sam build is executed, so I use shell script removing the folder before sam local start-api.
Read more