Fully Convolutional DenseNets for semantic segmentation.

Overview

Introduction

This repo contains the code to train and evaluate FC-DenseNets as described in The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation. We investigate the use of Densely Connected Convolutional Networks for semantic segmentation, and report state of the art results on datasets such as CamVid.

Installation

You need to install :

Data

The data loader is now available here : https://github.com/fvisin/dataset_loaders Thanks a lot to Francesco Visin, please cite if you use his data loader. Some adaptations may be do on the actual code, I hope to find some time to modify it !


The data-loader we used for the experiments will be released later. If you do want to train models now, you need to create a function load_data which returns 3 iterators (for training, validation and test). When applying next(), the iterator returns two values X, Y where X is the batch of input images (shape= (batch_size, 3, n_rows, n_cols), dtype=float32) and Y the batch of target segmentation maps (shape=(batch_size, n_rows, n_cols), dtype=int32) where each pixel in Y is an int indicating the class of the pixel.

The iterator must also have the following methods (so they are not python iterators) : get_n_classes (returns the number of classes), get_n_samples (returns the number of examples in the set), get_n_batches (returns the number of batches necessary to see the entire set) and get_void_labels (returns a list containing the classes associated to void). It might be easier to change directly the files train.py and test.py.

Run experiments

The architecture of the model is defined in FC-DenseNet.py. To train a model, you need to prepare a configuration file (folder config) where all the parameters needed for creating and training your model are precised. DenseNets contain lot of connections making graph optimization difficult for Theano. We strongly recommend to use the flags described further.

To train the FC-DenseNet103 model, use the command : THEANO_FLAGS='device=cuda,optimizer=fast_compile,optimizer_including=fusion' python train.py -c config/FC-DenseNet103.py -e experiment_name. All the logs of the experiments are stored in the folder experiment_name.

On a Titan X 12GB, for the model FC-DenseNet103 (see folder config), compilation takes around 400 sec and 1 epoch 120 sec for training and 40 sec for validation.

Use a pretrained model

We publish the weights of our model FC-DenseNet103. Metrics claimed in the paper (jaccard and accuracy) can be verified running THEANO_FLAGS='device=cuda,optimizer=fast_compile,optimizer_including=fusion' python test.py

About the "m" number in the paper

There is a small error with the "m" number in the Table 2 of the paper (that you may understand when running the code!). All values from the bottleneck to the last block (880, 1072, 800 and 368) should be incremented by 16 (896, 1088, 816 and 384).

Here how we compute this value representing the number of feature maps concatenated into the "stack" :

  • First convolution : m=48
  • In the downsampling part + bottleneck, m[B] = m[B-1] + n_layers[B] * growth_rate [linear growth]. First block : m = 48 + 4x16 = 112. Second block m = 112 + 5x16 = 192. Until the bottleneck : m = 656 + 15x16 = 896.
  • In the upsampling part, m[B] is the sum of 3 terms : the m value corresponding to same resolution in the downsampling part (skip connection), the number of feature maps from the upsampled block (n_layers[B-1] * growth_rate) and the number of feature maps in the new block (n_layers[B] * growth_rate). First upsampling, m = 656 + 15x16 + 12x16 = 1088. Second upsampling, m = 464 + 12x16 + 10x16 = 816. Third upsampling, m = 304 + 10x16 + 7x16 = 576, Fourth upsampling, m = 192 + 7x16 + 5x16 = 384 and fifth upsampling, m = 112 + 5x16 + 4x16 = 256
My personal code and solution to the Synacor Challenge from 2012 OSCON.

Synacor OSCON Challenge Solution (2012) This repository contains my code and solution to solve the Synacor OSCON 2012 Challenge. If you are interested

2 Mar 20, 2022
Efficient electromagnetic solver based on rigorous coupled-wave analysis for 3D and 2D multi-layered structures with in-plane periodicity

Efficient electromagnetic solver based on rigorous coupled-wave analysis for 3D and 2D multi-layered structures with in-plane periodicity, such as gratings, photonic-crystal slabs, metasurfaces, surf

Alex Song 17 Dec 19, 2022
Elevation Mapping on GPU.

Elevation Mapping cupy Overview This is a ros package of elevation mapping on GPU. Code are written in python and uses cupy for GPU calculation. * pla

Robotic Systems Lab - Legged Robotics at ETH Zürich 183 Dec 19, 2022
A curated list of references for MLOps

A curated list of references for MLOps

Larysa Visengeriyeva 9.3k Jan 07, 2023
AirLoop: Lifelong Loop Closure Detection

AirLoop This repo contains the source code for paper: Dasong Gao, Chen Wang, Sebastian Scherer. "AirLoop: Lifelong Loop Closure Detection." arXiv prep

Chen Wang 53 Jan 03, 2023
A PyTorch Library for Accelerating 3D Deep Learning Research

Kaolin: A Pytorch Library for Accelerating 3D Deep Learning Research Overview NVIDIA Kaolin library provides a PyTorch API for working with a variety

NVIDIA GameWorks 3.5k Jan 07, 2023
A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing.

AnimeGAN A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing. Randomly Generated Images The images are

Jie Lei 雷杰 1.2k Jan 03, 2023
A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 1.3x on an iPhone XS Max without sacrificing accuracy.

GFNet-Pytorch (NeurIPS 2020) This repo contains the official code and pre-trained models for the glance and focus network (GFNet). Glance and Focus: a

Rainforest Wang 169 Oct 28, 2022
Pytorch codes for "Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation"

Self-Supervised-MVS This repository is the official PyTorch implementation of our AAAI 2021 paper: "Self-supervised Multi-view Stereo via Effective Co

hongbin_xu 127 Jan 04, 2023
Manifold-Mixup implementation for fastai V2

Manifold Mixup Unofficial implementation of ManifoldMixup (Proceedings of ICML 19) for fast.ai (V2) based on Shivam Saboo's pytorch implementation of

Nestor Demeure 16 Jul 25, 2022
An open source Jetson Nano baseboard and tools to design your own.

My Jetson Nano Baseboard This basic baseboard gives the user the foundation and the flexibility to design their own baseboard for the Jetson Nano. It

NVIDIA AI IOT 57 Dec 29, 2022
Boostcamp CV Serving For Python

Boostcamp-CV-Serving Prerequisites MySQL GCP Cloud Storage GCP key file Sentry Streamlit Cloud Secrets: .streamlit/secrets.toml #DO NOT SHARE THIS I

Jungwon Seo 19 Feb 22, 2022
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

============================================================================================================ `MILA will stop developing Theano https:

9.6k Jan 06, 2023
This library is a location of the LegacyLogger for PyTorch Lightning.

neptune-contrib Documentation See neptune-contrib documentation site Installation Get prerequisites python versions 3.5.6/3.6 are supported Install li

neptune.ai 26 Oct 07, 2021
DL & CV-based indicator toolset for the vehicle drivers via live dash-cam footage.

Vehicle Indicator Toolset Deep Learning and Computer Vision based indicator toolset for vehicle drivers using live dash-cam footages. Tracking of vehi

Alex Xu 12 Dec 28, 2021
Semi-Supervised Learning for Fine-Grained Classification

Semi-Supervised Learning for Fine-Grained Classification This repo contains the code of: A Realistic Evaluation of Semi-Supervised Learning for Fine-G

25 Nov 08, 2022
Trustworthy AI related projects

Trustworthy AI This repository aims to include trustworthy AI related projects from Huawei Noah's Ark Lab. Current projects include: Causal Structure

HUAWEI Noah's Ark Lab 589 Dec 30, 2022
Video-based open-world segmentation

UVO_Challenge Team Alpes_runner Solutions This is an official repo for our UVO Challenge solutions for Image/Video-based open-world segmentation. Our

Yuming Du 84 Dec 22, 2022
Vision Transformer and MLP-Mixer Architectures

Vision Transformer and MLP-Mixer Architectures Update (2.7.2021): Added the "When Vision Transformers Outperform ResNets..." paper, and SAM (Sharpness

Google Research 6.4k Jan 04, 2023
From a body shape, infer the anatomic skeleton.

OSSO: Obtaining Skeletal Shape from Outside (CVPR 2022) This repository contains the official implementation of the skeleton inference from: OSSO: Obt

Marilyn Keller 166 Dec 28, 2022