U-Net Implementation: Convolutional Networks for Biomedical Image Segmentation" using the Carvana Image Masking Dataset in PyTorch

Last update: Jan 06, 2022

Overview

U-Net Implementation

By Christopher Ley

This is my interpretation and implementation of the famous paper "U-Net: Convolutional Networks for Biomedical Image Segmentation" using the Carvana Image Masking Dataset in PyTorch

This data set is a Binary Segmentation exercise of ~400 test images of cars from various angles such as those shown here:

Initial implementation for Binary Segmentation

The implementation performs almost as the winners of the competition (Dice: 0.9926 vs 0.99733) after only 5 epoch and we would expect the results to be as good as the winners using this architecture with more training and a little tweaking of the training hyper-parameters.

Here are the scores for training over 5 epochs by running:

(DeepLearning): python3 train.py

Training Results

0%|          | 0/540 [00:00<?, ?it/s]Accuracy: 103298971/467927040 = 22.08%
Dice score: 0.36127230525016785
100%|██████████| 540/540 [05:59<00:00,  1.50it/s, loss=0.0949]
==> Saving Checkpoint to: ./checkpoints/checkpoint_2022-01-06_12:39_epoch_0.pth.tar
Accuracy: 460498379/467927040 = 98.41%
Dice score: 0.9652246236801147
100%|██████████| 540/540 [05:59<00:00,  1.50it/s, loss=0.0469]
==> Saving Checkpoint to: ./checkpoints/checkpoint_2022-01-06_12:48_epoch_1.pth.tar
Accuracy: 461809183/467927040 = 98.69%
Dice score: 0.9711439609527588
100%|██████████| 540/540 [05:56<00:00,  1.51it/s, loss=0.0283]
==> Saving Checkpoint to: ./checkpoints/checkpoint_2022-01-06_12:56_epoch_2.pth.tar
Accuracy: 465675737/467927040 = 99.52%
Dice score: 0.9891990423202515
100%|██████████| 540/540 [06:00<00:00,  1.50it/s, loss=0.0194]
==> Saving Checkpoint to: ./checkpoints/checkpoint_2022-01-06_13:04_epoch_3.pth.tar
Accuracy: 465397979/467927040 = 99.46%
Dice score: 0.9878408908843994
100%|██████████| 540/540 [06:00<00:00,  1.50it/s, loss=0.0142]
==> Saving Checkpoint to: ./checkpoints/checkpoint_2022-01-06_13:12_epoch_4.pth.tar
Accuracy: 466399501/467927040 = 99.67%
Dice score: 0.9926225543022156

And an example of the output vs the ground truth of the validation set, I removed whole makes for the validation set, all 16 angles, the network had never seen this particular make from any angle.

Ground Truth

Prediction

Although limited in scope (binary segmentation for only cars), this architecture performs well with multiclass segmentation, I extended this to apply segmentation to the NYUv2 which is a multiclass objective, with little modification to the above code.

I will clean this up and upload the results and modifications soon!

U-Net Implementation: Convolutional Networks for Biomedical Image Segmentation" using the Carvana Image Masking Dataset in PyTorch

Related tags

Overview

U-Net Implementation

By Christopher Ley

Initial implementation for Binary Segmentation

Training Results

Ground Truth

Prediction

Owner

Christopher Ley

Generate image analogies using neural matching and blending

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction

Ivy is a templated deep learning framework which maximizes the portability of deep learning codebases.

Decentralized Reinforcment Learning: Global Decision-Making via Local Economic Transactions (ICML 2020)

Open-Domain Question-Answering for COVID-19 and Other Emergent Domains

Symbolic Parallel Adaptive Importance Sampling for Probabilistic Program Analysis in JAX

Alpha-Zero - Telegram Group Manager Bot Written In Python Using Pyrogram

Public Code for NIPS submission SimiGrad: Fine-Grained Adaptive Batching for Large ScaleTraining using Gradient Similarity Measurement

Self-Supervised Deep Blind Video Super-Resolution

A tf.keras implementation of Facebook AI's MadGrad optimization algorithm

Collection of generative models in Pytorch version.

DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow

Python Library for learning (Structure and Parameter) and inference (Statistical and Causal) in Bayesian Networks.

Implementation of our recent paper, WOOD: Wasserstein-based Out-of-Distribution Detection.

Exposure Time Calculator (ETC) and radial velocity precision estimator for the Near InfraRed Planet Searcher (NIRPS) spectrograph

Code for 'Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning', ICCV 2021

OCR Post Correction for Endangered Language Texts

Recreate CenternetV2 based on MMDET.