How exactly does LSTMCell from TensorFlow operates?

How exactly does LSTMCell from TensorFlow operates?

I try to reproduce results generated by the LSTMCell from TensorFlow to be sure that I know what it does.

I try to reproduce results generated by the LSTMCell from TensorFlow to be sure that I know what it does.

Here is my TensorFlow code:

num_units = 3
lstm = tf.nn.rnn_cell.LSTMCell(num_units = num_units)

timesteps = 7
num_input = 4
X = tf.placeholder("float", [None, timesteps, num_input])
x = tf.unstack(X, timesteps, 1)
outputs, states = tf.contrib.rnn.static_rnn(lstm, x, dtype=tf.float32)

sess = tf.Session()
init = tf.global_variables_initializer()

x_val = np.random.normal(size = (1, 7, num_input))

res =, feed_dict = {X:x_val})

for e in res:
    print e

Here is its output:

[[-0.13285545 -0.13569424 -0.23993783]]
[[-0.04818152  0.05927373  0.2558436 ]]
[[-0.13818116 -0.13837864 -0.15348436]]
[[-0.232219    0.08512601  0.05254192]]
[[-0.20371495 -0.14795329 -0.2261929 ]]
[[-0.10371902 -0.0263292  -0.0914975 ]]
[[0.00286371 0.16377522 0.059478  ]]

And here is my own implementation:

n_steps, _ = X.shape
h = np.zeros(shape = self.hid_dim)
c = np.zeros(shape = self.hid_dim)

for i in range(n_steps):
    x = X[i,:]

    vec = np.concatenate([x, h])
    #vec = np.concatenate([h, x])
    gs =, self.kernel) + self.bias

    g1 = gs[0*self.hid_dim : 1*self.hid_dim]
    g2 = gs[1*self.hid_dim : 2*self.hid_dim]
    g3 = gs[2*self.hid_dim : 3*self.hid_dim]
    g4 = gs[3*self.hid_dim : 4*self.hid_dim]

    I = vsigmoid(g1)
    N = np.tanh(g2)
    F = vsigmoid(g3)
    O = vsigmoid(g4)

    c = c*F + I*N

    h = O * np.tanh(c)

    print h

And here is its output:

[-0.13285543 -0.13569425 -0.23993781]
[-0.01461723  0.08060743  0.30876374]
[-0.13142865 -0.14921292 -0.16898363]
[-0.09892188  0.11739943  0.08772941]
[-0.15569218 -0.15165766 -0.21918869]
[-0.0480604  -0.00918626 -0.06084118]
[0.0963612  0.1876516  0.11888081]

As you might notice I was able to reproduce the first hidden vector, but the second one and all the following ones are different. What am I missing?

python tensorflow

Bootstrap 5 Complete Course with Examples

Bootstrap 5 Tutorial - Bootstrap 5 Crash Course for Beginners

Nest.JS Tutorial for Beginners

Hello Vue 3: A First Look at Vue 3 and the Composition API

Building a simple Applications with Vue 3

Deno Crash Course: Explore Deno and Create a full REST API with Deno

How to Build a Real-time Chat App with Deno and WebSockets

Convert HTML to Markdown Online

HTML entity encoder decoder Online

Basic Data Types in Python | Python Web Development For Beginners

In the programming world, Data types play an important role. Each Variable is stored in different data types and responsible for various functions. Python had two different objects, and They are mutable and immutable objects.

How To Compare Tesla and Ford Company By Using Magic Methods in Python

Magic Methods are the special methods which gives us the ability to access built in syntactical features such as ‘<’, ‘>’, ‘==’, ‘+’ etc.. You must have worked with such methods without knowing them to be as magic methods. Magic methods can be identified with their names which start with __ and ends with __ like __init__, __call__, __str__ etc. These methods are also called Dunder Methods, because of their name starting and ending with Double Underscore (Dunder).

Python Programming: A Beginner’s Guide

Python is an interpreted, high-level, powerful general-purpose programming language. You may ask, Python’s a snake right? and Why is this programming language named after it?

Hire Python Developers

Are you looking for experienced, reliable, and qualified Python developers? If yes, you have reached the right place. At **[]( "")**, our full-stack Python development services...

Python any: How to Check If Element is Iterable or Not

Python any() function returns True if any element of an iterable is True otherwise any() function returns False. The syntax is any().