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

Unofficial TensorFlow implementation of the Keyword Spotting Transformer model

A clear, concise, simple yet powerful and efficient API for deep learning.

Official implementation of the NRNS paper: No RL, No Simulation: Learning to Navigate without Navigating

A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation

PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models

Active Offline Policy Selection With Python

Pytorch implementation of CVPR2020 paper “VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation”

Codebase for Inducing Causal Structure for Interpretable Neural Networks

Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs

Pytorch code for semantic segmentation using ERFNet

Rendering Point Clouds with Compute Shaders

Compositional Sketch Search

Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning

Official Pytorch Implementation of Length-Adaptive Transformer (ACL 2021)

A custom DeepStack model that has been trained detecting ONLY the USPS logo

This is the official pytorch implementation of the BoxEL for the description logic EL++

DRIFT is a tool for Diachronic Analysis of Scientific Literature.

A new test set for ImageNet

Fast, general, and tested differentiable structured prediction in PyTorch

This is the code for our paper "Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text"