Consider the following example: a=tf.constant([[1,2,3],[4,5,6]],shape=(2,3),name=”a”) b=a+1 It will produce the following graph: We can see a constant tensorflow operation has two attributes: dtype is the type of the elements stored […]
Consider the following example: i = tf.get_variable(“i”, dtype=tf.int32, shape=[], initializer=tf.ones_initializer()) n = tf.constant(10) def cond(a, n): return a< n def body(a, n): a = a + 2 return a, n […]
A RNN(Recurrent Neural Network) layer is composed of a set of recurrent neurons. The output of each recurrent neuron is dependent not only on the input vector but also the […]
It is interesting to know the fact that some visual neurons reacts to only part of the region we can see(so called local receptive field). This is contrary to institution […]
Cuda and CuDNN. CuDNN is based on CUDA. install tensorflow for GPU: pip install tensorflow-gpu set the environment variable CUDA_VISIBLE_DEVICES=3,2 then run a tensorflow program to let the tensorflow program […]
To understand the content of this chapter, we need to review the concept about gradient and gradient descent. Gradient descent algorithm was introduced in chapter 4. In that chapter, a […]
In Linux, you can compute the md5 of a file using the md5 command. md5 file You can compare the output of the md5 with the md5 published on the […]
Knowing the version of Python and tensorflow currently installed on your PC is important as tensorflow may not run on the latest version of python, or you installed a 32-bit […]
The python with statement is a little strange to programmers of other languages. It is frequently occurred in tensorflow related codes like: with tf.Session() as sess: do something A new […]
When you debug a QtWebEngine application, you may use qDebug to print information here and there. You need to turn on the console by adding a line “CONFIG += console” […]