PyTorch implementation of ENet

Overview

PyTorch-ENet

PyTorch (v1.1.0) implementation of ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation, ported from the lua-torch implementation ENet-training created by the authors.

This implementation has been tested on the CamVid and Cityscapes datasets. Currently, a pre-trained version of the model trained in CamVid and Cityscapes is available here.

Dataset Classes 1 Input resolution Batch size Epochs Mean IoU (%) GPU memory (GiB) Training time (hours)2
CamVid 11 480x360 10 300 52.13 4.2 1
Cityscapes 19 1024x512 4 300 59.54 5.4 20

1 When referring to the number of classes, the void/unlabeled class is always excluded.
2 These are just for reference. Implementation, datasets, and hardware changes can lead to very different results. Reference hardware: Nvidia GTX 1070 and an AMD Ryzen 5 3600 3.6GHz. You can also train for 100 epochs or so and get similar mean IoU (± 2%).
3 Test set.
4 Validation set.

Installation

Local pip

  1. Python 3 and pip
  2. Set up a virtual environment (optional, but recommended)
  3. Install dependencies using pip: pip install -r requirements.txt

Docker image

  1. Build the image: docker build -t enet .
  2. Run: docker run -it --gpus all --ipc host enet

Usage

Run main.py, the main script file used for training and/or testing the model. The following options are supported:

python main.py [-h] [--mode {train,test,full}] [--resume]
               [--batch-size BATCH_SIZE] [--epochs EPOCHS]
               [--learning-rate LEARNING_RATE] [--lr-decay LR_DECAY]
               [--lr-decay-epochs LR_DECAY_EPOCHS]
               [--weight-decay WEIGHT_DECAY] [--dataset {camvid,cityscapes}]
               [--dataset-dir DATASET_DIR] [--height HEIGHT] [--width WIDTH]
               [--weighing {enet,mfb,none}] [--with-unlabeled]
               [--workers WORKERS] [--print-step] [--imshow-batch]
               [--device DEVICE] [--name NAME] [--save-dir SAVE_DIR]

For help on the optional arguments run: python main.py -h

Examples: Training

python main.py -m train --save-dir save/folder/ --name model_name --dataset name --dataset-dir path/root_directory/

Examples: Resuming training

python main.py -m train --resume True --save-dir save/folder/ --name model_name --dataset name --dataset-dir path/root_directory/

Examples: Testing

python main.py -m test --save-dir save/folder/ --name model_name --dataset name --dataset-dir path/root_directory/

Project structure

Folders

  • data: Contains instructions on how to download the datasets and the code that handles data loading.
  • metric: Evaluation-related metrics.
  • models: ENet model definition.
  • save: By default, main.py will save models in this folder. The pre-trained models can also be found here.

Files

  • args.py: Contains all command-line options.
  • main.py: Main script file used for training and/or testing the model.
  • test.py: Defines the Test class which is responsible for testing the model.
  • train.py: Defines the Train class which is responsible for training the model.
  • transforms.py: Defines image transformations to convert an RGB image encoding classes to a torch.LongTensor and vice versa.
Owner
David Silva
:eyes:🚗
David Silva
Pretrained models for Jax/Haiku; MobileNet, ResNet, VGG, Xception.

Pre-trained image classification models for Jax/Haiku Jax/Haiku Applications are deep learning models that are made available alongside pre-trained we

Alper Baris CELIK 14 Dec 20, 2022
Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization

FAC-Net Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization Linjiang Huang (CUHK), Liang Wang (CASIA), Hongsheng

21 Nov 22, 2022
Dictionary Learning with Uniform Sparse Representations for Anomaly Detection

Dictionary Learning with Uniform Sparse Representations for Anomaly Detection Implementation of the Uniform DL Representation for AD algorithm describ

Paul Irofti 1 Nov 23, 2022
Reproducing Results from A Hybrid Approach to Targeting Social Assistance

title author date output Reproducing Results from A Hybrid Approach to Targeting Social Assistance Lendie Follett and Heath Henderson 12/28/2021 html_

Lendie Follett 0 Jan 06, 2022
A tool to analyze leveraged liquidity mining and find optimal option combination for hedging.

LP-Option-Hedging Description A Python program to analyze leveraged liquidity farming/mining and find the optimal option combination for hedging imper

Aureliano 18 Dec 19, 2022
Code for STFT Transformer used in BirdCLEF 2021 competition.

STFT_Transformer Code for STFT Transformer used in BirdCLEF 2021 competition. The STFT Transformer is a new way to use Transformers similar to Vision

Jean-François Puget 69 Sep 29, 2022
A simple and useful implementation of LPIPS.

lpips-pytorch Description Developing perceptual distance metrics is a major topic in recent image processing problems. LPIPS[1] is a state-of-the-art

So Uchida 121 Dec 24, 2022
WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU

WarpDrive is a flexible, lightweight, and easy-to-use open-source reinforcement learning (RL) framework that implements end-to-end multi-agent RL on a single GPU (Graphics Processing Unit).

Salesforce 334 Jan 06, 2023
Codes and pretrained weights for winning submission of 2021 Brain Tumor Segmentation (BraTS) Challenge

Winning submission to the 2021 Brain Tumor Segmentation Challenge This repo contains the codes and pretrained weights for the winning submission to th

94 Dec 28, 2022
95.47% on CIFAR10 with PyTorch

Train CIFAR10 with PyTorch I'm playing with PyTorch on the CIFAR10 dataset. Prerequisites Python 3.6+ PyTorch 1.0+ Training # Start training with: py

5k Dec 30, 2022
Config files for my GitHub profile.

Canalyst Candas Data Science Library Name Canalyst Candas Description Built by a former PM / analyst to give anyone with a little bit of Python knowle

Canalyst Candas 13 Jun 24, 2022
The pytorch implementation of the paper "text-guided neural image inpainting" at MM'2020

TDANet: Text-Guided Neural Image Inpainting, MM'2020 (Oral) MM | ArXiv This repository implements the paper "Text-Guided Neural Image Inpainting" by L

LisaiZhang 75 Dec 22, 2022
Good Semi-Supervised Learning That Requires a Bad GAN

Good Semi-Supervised Learning that Requires a Bad GAN This is the code we used in our paper Good Semi-supervised Learning that Requires a Bad GAN Ziha

Zhilin Yang 177 Dec 12, 2022
Multi-scale discriminator feature-wise loss function

Multi-Scale Discriminative Feature Loss This repository provides code for Multi-Scale Discriminative Feature (MDF) loss for image reconstruction algor

Graphics and Displays group - University of Cambridge 76 Dec 12, 2022
Official Implementation of Neural Splines

Neural Splines: Fitting 3D Surfaces with Inifinitely-Wide Neural Networks This repository contains the official implementation of the CVPR 2021 (Oral)

Francis Williams 56 Nov 29, 2022
[NeurIPS 2021] "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators"

G-PATE This is the official code base for our NeurIPS 2021 paper: "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of T

AI Secure 14 Oct 12, 2022
YOLOv2 in PyTorch

YOLOv2 in PyTorch NOTE: This project is no longer maintained and may not compatible with the newest pytorch (after 0.4.0). This is a PyTorch implement

Long Chen 1.5k Jan 02, 2023
Discord bot-CTFD-Thread-Parser - Discord bot CTFD-Thread-Parser

Discord bot CTFD-Thread-Parser Description: This tools is used to create automat

15 Mar 22, 2022
yufan 81 Dec 08, 2022
The official implementation of paper Siamese Transformer Pyramid Networks for Real-Time UAV Tracking, accepted by WACV22

SiamTPN Introduction This is the official implementation of the SiamTPN (WACV2022). The tracker intergrates pyramid feature network and transformer in

Robotics and Intelligent Systems Control @ NYUAD 29 Jan 08, 2023