https://github.com/himanshurawlani/practical_intro_to_tf2

Building an image classifier in TF2
https://github.com/himanshurawlani/practical_intro_to_tf2

image-classifier tensorflow tensorflow-2 tensorflow-datasets tensorflow-serving tf-keras

Last synced: about 2 months ago
JSON representation

Building an image classifier in TF2

• Host: GitHub
• URL: https://github.com/himanshurawlani/practical_intro_to_tf2
• Owner: himanshurawlani
• License: mit
• Created: 2019-03-10T18:23:34.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2019-12-28T18:14:50.000Z (almost 5 years ago)
• Last Synced: 2024-08-01T03:14:39.906Z (4 months ago)
• Topics: image-classifier, tensorflow, tensorflow-2, tensorflow-datasets, tensorflow-serving, tf-keras
• Language: Jupyter Notebook
• Size: 43.9 MB
• Stars: 55
• Watchers: 3
• Forks: 22
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-tensorflow-2 - Practical intro to tf2

README

        
# Practical Introduction to TensorFlow 2.0

This repository introduces the new Tensorflow 2.0 in a practical way by building an image classifier which classifies 5 classes of flowers. It covers the following:

1. Downloading and preprocessing data using TensorFlow Datasets

* Checking out available datasets and their features

* Downloading the dataset (tfds.load()))

* Pre-processing the dataset

* Visualizing the dataset

2. Building and training an image classifier model using Keras high level API

* Building a simple CNN in Keras

* Visualising the model

* Compiling and training the model

* Training the model using data augmentation

* Using TensorBoard inside notebooks

3. Downloading and fine-tuning InceptionV3 pre-trained model

* Downloading pre-trained model

* Adding classification head

* Training the classification head

* Fine tuning the model

4. Serving the trained model using TensorFlow Serving

* Tensorflow Serving installation

* Starting TensorFlow Serving

* Making REST requests

* Parsing the response

Read the Medium article explaining the above concepts in detail [here](https://medium.com/@himanshurawlani/getting-started-with-tensorflow-2-0-faf5428febae?source=friends_link&sk=216dd7c2de38e8344737221768126b14).