TensorFlow2.0-Examples

This tutorial was designed for easily diving into TensorFlow2.0. it includes both notebooks and source codes with explanation. It will be continuously updated ! 🐍🐍🐍🐍🐍🐍

Contents

1 - Introduction

• Hello World (notebook) (code). Very simple example to learn how to print "hello world" using TensorFlow.
• Variable (notebook) (code). Learn to use variable in tensorflow.
• Basical operation (notebook) (code). A simple example that covers TensorFlow basic operations.
• Activation (notebook) (code). Start to know some activation functions in tensorflow.
• GradientTape (notebook) (code). Introduce a key technique for automatic differentiation

2 - Basical Models

• Linear Regression (notebook) (code). Implement a Linear Regression with TensorFlow.
• Logistic Regression (notebook) (code). Implement a Logistic Regression with TensorFlow.
• Multilayer Perceptron Layer (notebook) (code). Implement Multi-Layer Perceptron Model with TensorFlow.
• CNN (notebook) (code). Implement CNN Model with TensorFlow.

3 - Neural Network Architecture

• VGG16 (notebook) (code)(paper). VGG16: Very Deep Convolutional Networks for Large-Scale Image Recognition.
• Resnet (notebook) (code)(paper). Resnet: Deep Residual Learning for Image Recognition. 🔥🔥🔥
• AutoEncoder (notebook) (code)(paper). AutoEncoder: Reducing the Dimensionality of Data with Neural Networks.

• FPN (notebook) (code)(paper). FPN: Feature Pyramid Networks for Object Detection.

4 - Object Detection

• RPN (notebook) (code)(paper). RPN: a Region Proposal Network 🔥🔥🔥🔥🔥

• MTCNN (notebook) (code)(paper). MTCNN: Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks. (Face detection and Alignment) 🔥🔥

• YOLOv3 (notebook) (code)(paper). YOLOv3: An Incremental Improvement.🔥🔥🔥🔥

• SSD (notebook) (code)(paper). SSD: Single Shot MultiBox Detector.🔥🔥🔥🔥 【TO DO】

• Faster R-CNN (notebook) (code)(paper). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.🔥🔥🔥🔥 【TO DO】

5 - Image Segmentation

• FCN (notebook) (code)(paper). FCN: Fully Convolutional Networks for Semantic Segmentation. 🔥🔥🔥🔥🔥

• Unet (notebook) (code)(paper). U-Net: Convolutional Networks for Biomedical Image Segmentation. 🔥🔥

6 - Generative Adversarial Networks

• DCGAN (notebook) (code)(paper). Deep Convolutional Generative Adversarial Network.
• Pix2Pix (notebook) (code)(paper). Image-to-Image Translation with Conditional Adversarial Networks.

7 - Utils

• Multiple GPU Training (notebook)(code). Use multiple GPU to train your model.