Skip to content
/ practical-machine-learining-with-tensorflow Public

Teaching materials for the probabilistic graphical models and deep learning classes at nptel

2 stars 2 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

vipulgote1999/practical-machine-learining-with-tensorflow

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
.github/workflows
.github/workflows
 
 
CNNs_Part1.ipynb
CNNs_Part1.ipynb
 
 
Copy_of_Assignment_6_practical_machine_learning_Estimators.ipynb
Copy_of_Assignment_6_practical_machine_learning_Estimators.ipynb
 
 
GAN on fashion mnist dataset.ipynb
GAN on fashion mnist dataset.ipynb
 
 
README.md
README.md
 
 
Understanding_recurrent_neural_networks.ipynb
Understanding_recurrent_neural_networks.ipynb
 
 
basic_classification.ipynb
basic_classification.ipynb
 
 
basic_regression.ipynb
basic_regression.ipynb
 
 
basic_text_classification_with_tfhub.ipynb
basic_text_classification_with_tfhub.ipynb
 
 
boosted_trees.ipynb
boosted_trees.ipynb
 
 
csv.ipynb
csv.ipynb
 
 
data.ipynb
data.ipynb
 
 
feature_columns.ipynb
feature_columns.ipynb
 
 
from_pandas.ipynb
from_pandas.ipynb
 
 
image_classification_and_visualization.ipynb
image_classification_and_visualization.ipynb
 
 
images.ipynb
images.ipynb
 
 
linear.ipynb
linear.ipynb
 
 
numpy.ipynb
numpy.ipynb
 
 
overfit_and_underfit.ipynb
overfit_and_underfit.ipynb
 
 
premade.ipynb
premade.ipynb
 
 
save_and_restore_models.ipynb
save_and_restore_models.ipynb
 
 
text.ipynb
text.ipynb
 
 
text_classification_rnn.ipynb
text_classification_rnn.ipynb
 
 
text_generation.ipynb
text_generation.ipynb
 
 
tf_text.ipynb
tf_text.ipynb
 
 
time_series.ipynb
time_series.ipynb
 
 
transfer_learning_with_hub.ipynb
transfer_learning_with_hub.ipynb
 
 
unicode.ipynb
unicode.ipynb
 
 
word_embeddings.ipynb
word_embeddings.ipynb
 
 

Repository files navigation

Welcome to Practical Machine Learning with TensorFlow 2.0 MOOC. As the name suggests we will mainly focus on practical aspects of ML that involves writing code in Python with TensorFlow 2.0 API. In every session, we will review the concept from theory point of view and then jump straight into implementation. We will be using Google Colab as a platform for coding these models. We will mainly cover material from the following page: https://www.tensorflow.org/beta

I would strongly advise students to run the code and experience how the code works. Once you get the basic idea of the concept and its implementation, you can spend some time looking at the details of each function from TF RC 2.0 API.

We will learn how to use tf.Keras and tf.Estimator APIs for building models. We will also learn to use tf.Dataset API for building input pipelines for bringing data to ML models. Later in the course, we will learn how to build customized ML models and train them in distributed fashion.

Wish you a great journey of learning TensorFlow with us!

About

Teaching materials for the probabilistic graphical models and deep learning classes at nptel

Resources

Readme
Activity

Stars

2 stars

Watchers

1 watching

Forks

2 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages