...

Artificial Intelligence - Tensorflow

Back to Course

Lesson Description


Lession - #1022 Tensorflow TensorBoard Visualization


TensorBoard Visualization

TensorFlow incorporates a representation apparatus, which is known as the TensorBoard. It is utilized for dissecting Data Flow Graph and furthermore used to comprehend AI models. The significant component of TensorBoard incorporates a perspective on various kinds of measurements about the boundaries and subtleties of any chart in vertical arrangement.

Profound brain network incorporates up to 36,000 hubs. TensorBoard aides in falling these hubs in significant level squares and featuring the indistinguishable designs. This permits better examination of chart zeroing in on the essential areas of the calculation diagram. The TensorBoard representation is supposed to be extremely intelligent where a client can skillet, zoom and extend the hubs to show the subtleties.

The accompanying schematic chart portrayal shows the total working of TensorBoard perception −



The calculations breakdown hubs into undeniable level squares and feature the particular gatherings with indistinguishable designs, what separate serious level hubs. The TensorBoard hence made is helpful and is dealt with similarly significant for tuning an AI model. This perception apparatus is intended for the setup log document with outline data and subtleties that should be shown.

Allow us to zero in on the demo illustration of TensorBoard perception with the assistance of the accompanying code −


import tensorflow as tf 

# Constants creation for TensorBoard visualization 
a = tf.constant(10,name = "a">
b = tf.constant(90,name = "b">
y = tf.Variable(a+b*2,name = 'y'>
model = tf.initialize_all_variables(>
#Creation of model with tf.Session(>
as session: merged = tf.merge_all_summaries(>
writer = tf.train.SummaryWriter("/tmp/tensorflowlogs",session.graph>
session.run(model>
print(session.run(y>
>


Can I get a job with TensorFlow?
Well, the answer is yes. Be it freelancing or working a 9-5 in your dream software developer company, whatever the case, you can be sure that learning this skill will be worth your time and effort, especially if you want a high-paying job. The average TensorFlow developer salary is about $148,508.