🗺 General purpose U-Network implemented in Keras for image segmentation

Or Fleisher

Last update: Aug 31, 2022

Overview

TF-Unet

General purpose U-Network implemented in Keras for image segmentation

Getting started • Training • Evaluation

Getting started

Looking for Jupyter notebooks? checkout the training, evaulation and prediction notebooks or run make jupyter to serve them locally. Looking for pre-trained weights? download them here.

Dependencies

To quickly get started make sure you have the following dependencies installed:

Docker (19 or newer) 📦
Make [Optional macOS / Linux] 🛠
Nvidia Container Toolkit [Optional for GPUs] 🗜

Setup

Clone (or download) the repository and cd into it

git clone https://github.com/juniorxsound/TF-Unet.git && cd TF-Unet

Next build the Docker image by simply running make build

The build process will pick either Dockerfile.cpu or Dockerfile.gpu based on your system

Training

This repository uses the ShapeDataset synthetic data generator written by Matterport (in Mask R-CNN). No download is needed, as all data is generated during runtime, here is a sample of the dataset

To start training, simply call make train which will start the training process using the parameters defined in train.py. A model will be saved at the end of the training process into the weights folder in SavedModel format.

If you are interested in following the training process, you can use make log during training to start a Tensorboard server with accuracy and loss metrics being updated every batch.

Tensorboard image here

If you want to train in a Jupyter notebook follow the Training notebook

Evaluation

To quickly evaluate download the pre-trained weights and unzip the contents into the weights folder. To run evaluation simply use make evaluate or the Jupyter Evaluation notebook.

The weights provided were trained for 50 epochs on 8000 samples with batch size of 18. Training takes 5 hours using 2 GTX 2080ti's and reaches 96.56% accuracy.

Prediction

See the Jupyter Prediction notebook.

Architecture

The implementation was inspired by U-Net: Convolutional Networks for Biomedical Image Segmentation

Thanks to

The original paper authors, this Keras UNet implementation, this Tensorflow UNet implementation and Mask R-CNN authors.

Comments

Cache docker image on CI so it runs faster 🏃🏿‍♀️

Is your feature request related to a problem? Please describe. Right now Travis is building the image every time there is a commit, regardless of whether the image itself changed or not. This takes almost 5 minutes where it could really be just using the :latest tag from the previous build

Describe the solution you'd like Cache the :latest image build and only rebuild the layers that changed (if any).

Additional context Some more context in this post
enhancement 🏋🏾‍♀️ nice to have 🎁

opened by juniorxsound 0

This source code is implemented using keras library based on "Automatic ocular artifacts removal in EEG using deep learning"

CSP_Deep_EEG This source code is implemented using keras library based on "Automatic ocular artifacts removal in EEG using deep learning" {https://www

2 Nov 8, 2022

A python-image-classification web application project, written in Python and served through the Flask Microframework. This Project implements the VGG16 covolutional neural network, through Keras and Tensorflow wrappers, to make predictions on uploaded images.

Image Classification in Python Implementing image classification in Flask using Keras. The VGG16 is a convolution neural network model architecture th

19 Dec 12, 2022

Worktory is a python library created with the single purpose of simplifying the inventory management of network automation scripts.

18 Aug 31, 2022

🗺 General purpose U-Network implemented in Keras for image segmentation

Related tags

Overview

TF-Unet

Getting started

Dependencies

Setup

Training

Evaluation

Prediction

Architecture

Thanks to

You might also like...

This source code is implemented using keras library based on "Automatic ocular artifacts removal in EEG using deep learning"

This is an implementation of Googles Yogi-Optimizer in Keras (tf.keras)

Keras udrl - Keras implementation of Upside Down Reinforcement Learning

Example-custom-ml-block-keras - Custom Keras ML block example for Edge Impulse

Classification models 1D Zoo - Keras and TF.Keras

A keras-based real-time model for medical image segmentation (CFPNet-M)

Official implementation of "SinIR: Efficient General Image Manipulation with Single Image Reconstruction" (ICML 2021)

A python-image-classification web application project, written in Python and served through the Flask Microframework. This Project implements the VGG16 covolutional neural network, through Keras and Tensorflow wrappers, to make predictions on uploaded images.

Worktory is a python library created with the single purpose of simplifying the inventory management of network automation scripts.

Comments

Cache docker image on CI so it runs faster 🏃🏿‍♀️

Owner

Or Fleisher

Implementation of self-attention mechanisms for general purpose. Focused on computer vision modules. Ongoing repository.

a general-purpose Transformer based vision backbone

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

A task-agnostic vision-language architecture as a step towards General Purpose Vision

A general-purpose, flexible, and easy-to-use simulator alongside an OpenAI Gym trading environment for MetaTrader 5 trading platform (Approved by OpenAI Gym)

Unofficial PyTorch implementation of MobileViT based on paper "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer".

General purpose GPU compute framework for cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends)

A general-purpose programming language, focused on simplicity, safety and stability.

We have implemented shaDow-GNN as a general and powerful pipeline for graph representation learning. For more details, please find our paper titled Deep Graph Neural Networks with Shallow Subgraph Samplers, available on arXiv (https//arxiv.org/abs/2012.01380).

DFFNet: An IoT-perceptive Dual Feature Fusion Network for General Real-time Semantic Segmentation