Image Segmentation using Deeplab v3+

Experimenting with Quantization of Tensorflow Models on various datasets with the DeepLab v3 Decoder architecture and MobileNet v2 Encoder architectureusing using a variety of techniques including

• Quantization aware training
• Quantization aware training with delay
• Post training Quantization
• Quantized Inference/Evalulation

• Lighter, Faster Semantic Segmentation by Post-Training Quantization and Quantization-Aware Training

@inproceedings{deeplabv3plus2018, title={Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation}, author={Liang-Chieh Chen and Yukun Zhu and George Papandreou and Florian Schroff and Hartwig Adam}, booktitle={ECCV}, year={2018} }

pip install all the following required packages.

• TensorFlow 1.15
• Jupyter Notebook
• Python 3.6
• Numpy
• Pillow
• matplotlib
• conda

Note: For a ready to use envirenment, a deeplearning ami on an EC2 instance would come with all the required packages needed to run this repo immediatly.

• Fine-tuning and Quantization

• Inference

• clone the repo
• navigate to ImageSegmentationWithDeeplab (command: cd ImageSegmentationWithDeeplab)
• run the command "jupyter notebook"
• use the provided url (default: localhost:8888)
• open the "inference_deeplab.ipynb" notebook
• From drop down list Cell > Run All

• FLOAT32 Segmentation

• Post-Quantization UINT8 Segmentation (no fine-tuning)

• Post-Quantization UINT8 Segmentation (10K-iteration fine-tuning)

• Quantization-Aware-Training UNIT8 Segmentation

This page (code, report and presentation) is the group "E" submission for Final project for CS256: Selected Topics in Artificial Intelligence, Section 2. Leb by Instructor: Mashhour Solh, Ph.D.
The group members are:

• Sherif Elsaid
• Inhee Park
• Sagar Shahi
• Sriram Priyatham Siram
• Anand Vishwakarma

This project was conducted with free credits provided by AWS educate team.