Retinal vessel segmentation based on GT-UNet

Last update: Dec 18, 2022

Related tags

Overview

Retinal vessel segmentation based on GT-UNet

Introduction

This project is a retinal blood vessel segmentation code based on UNet-like Group Transformer Network (GT-UNet), including data preprocessing, model training and testing, visualization, etc.

Requirements

The main package and version of the python environment are as follows

# Name                    Version         
python                    3.7.9                    
pytorch                   1.7.0         
torchvision               0.8.0         
cudatoolkit               10.2.89       
cudnn                     7.6.5           
matplotlib                3.3.2              
numpy                     1.19.2        
opencv                    3.4.2         
pandas                    1.1.3        
pillow                    8.0.1         
scikit-learn              0.23.2          
scipy                     1.5.2           
tensorboardX              2.1        
tqdm                      4.54.1

Usage

The project structure and intention are as follows :

VesselSeg-Pytorch			# Source code		
    ├── config.py		 	# Configuration information
    ├── lib			            # Function library
    │   ├── common.py
    │   ├── dataset.py		        # Dataset class to load training data
    │   ├── datasetV2.py		        # Dataset class to load training data with lower memory
    │   ├── extract_patches.py		# Extract training and test samples
    │   ├── help_functions.py		# 
    │   ├── __init__.py
    │   ├── logger.py 		        # To create log
    │   ├── losses
    │   ├── metrics.py		        # Evaluation metrics
    │   └── pre_processing.py		# Data preprocessing
    ├── models		        # All models are created in this folder
    │   ├── __init__.py
    │   ├── nn
    │   └── GT-UNet.py
    ├── prepare_dataset	        # Prepare the dataset (organize the image path of the dataset)
    │   ├── chasedb1.py
    │   ├── data_path_list		  # image path of dataset
    │   ├── drive.py
    │   └── stare.py
    ├── tools			     # some tools
    │   ├── ablation_plot.py
    │   ├── ablation_plot_with_detail.py
    │   ├── merge_k-flod_plot.py
    │   └── visualization
    ├── function.py			        # Creating dataloader, training and validation functions 
    ├── test.py			            # Test file
    └── train.py			          # Train file

Training model

Please confirm the configuration information in the config.py. Pay special attention to the train_data_path_list and test_data_path_list. Then, running:

python train.py

You can configure the training information in config, or modify the configuration parameters using the command line. The training results will be saved to the corresponding directory(save name) in the experiments folder.

3) Testing model

The test process also needs to specify parameters in config.py. You can also modify the parameters through the command line, running:

python test.py

The above command loads the best_model.pth in ./experiments/GT-UNet_vessel_seg and performs a performance test on the testset, and its test results are saved in the same folder.

Retinal vessel segmentation based on GT-UNet

Related tags

Overview

Retinal vessel segmentation based on GT-UNet

Introduction

Requirements

Usage

Training model

3) Testing model

Owner

Kent0n

A Domain-Agnostic Benchmark for Self-Supervised Learning

Sign Language is detected in realtime using video sequences. Our approach involves MediaPipe Holistic for keypoints extraction and LSTM Model for prediction.

Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation

GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot

A Fast Knowledge Distillation Framework for Visual Recognition

The code of paper "Block Modeling-Guided Graph Convolutional Neural Networks".

Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis

Code and datasets for the paper "Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction" (RA-L, 2021)

Code of the lileonardo team for the 2021 Emotion and Theme Recognition in Music task of MediaEval 2021

This porject is intented to build the most accurate model for predicting the porbability of loan default

MAGMA - a GPT-style multimodal model that can understand any combination of images and language

AOT-GAN for High-Resolution Image Inpainting (codebase for image inpainting)

Gradient-free global optimization algorithm for multidimensional functions based on the low rank tensor train format

We present a regularized self-labeling approach to improve the generalization and robustness properties of fine-tuning.

Storage-optimizer - Identify potintial optimizations on the cloud storage accounts

Pytorch codes for "Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation"

Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

PyTorch implementation of "Debiased Visual Question Answering from Feature and Sample Perspectives" (NeurIPS 2021)

Implementation for Shape from Polarization for Complex Scenes in the Wild