This repository contains the code for "SBEVNet: End-to-End Deep Stereo Layout Estimation" paper by Divam Gupta, Wei Pu, Trenton Tabor, Jeff Schneider

Overview

SBEVNet: End-to-End Deep Stereo Layout Estimation

This repository contains the code for "SBEVNet: End-to-End Deep Stereo Layout Estimation" paper by Divam Gupta, Wei Pu, Trenton Tabor, Jeff Schneider

Usage

Dependencies

pip install --upgrade git+https://github.com/divamgupta/pytorch-propane
pip install torch==1.4.0 torchvision==0.5.0
pip install opencv-python
pip install torchgeometry

Dataset and Directories

For the example we use the following directories:

  • Datasets : ./datasets/carla/ and ./datasets/kitti/
  • Weights : ./sbevnet_weights/carla and ./sbevnet_weights/kitti
  • Predictions : ./predictions/kitti ./predictions/carla

Download and unzip the datasets and place them in ./datasets directory

Training

cd <cloned_repo_path>

Training the model on the CARLA dataset:

pytorch_propane sbevnet train    \
 --model_name sbevnet_model --network_name sbevnet --dataset_name  sbevnet_dataset_main --dataset_split train \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test \
 --batch_size 3  --eval_batch_size 1 \
 --n_epochs 20   --overwrite_epochs true  \
 --datapath "datasets/carla/dataset.json" \
 --save_path "sbevnet_weights/carla/carla_save_0" \
 --image_w 512 \
 --image_h 288 \
 --max_disp 64 \
 --n_hmap 100 \
 --xmin 1 \
 --xmax 39 \
 --ymin -19 \
 --ymax 19 \
 --cx 256 \
 --cy 144 \
 --f 179.2531 \
 --tx 0.2 \
 --camera_ext_x 0.9 \
 --camera_ext_y -0.1 \
 --fixed_cam_confs true \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true --check_degenerate true 

Training the model on the KITTI dataset:

pytorch_propane sbevnet train    \
 --model_name sbevnet_model --network_name sbevnet --dataset_name  sbevnet_dataset_main --dataset_split train \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test \
 --batch_size 3  --eval_batch_size 1 \
 --n_epochs 40   --overwrite_epochs true  \
 --datapath "datasets/kitti/dataset.json" \
 --save_path "sbevnet_weights/kitti/kitti_save_0" \
 --image_w 640 \
 --image_h 256 \
 --max_disp 64 \
 --n_hmap 128 \
 --xmin 5.72 \
 --xmax 43.73 \
 --ymin -19 \
 --ymax 19 \
 --camera_ext_x 0 \
 --camera_ext_y 0 \
 --fixed_cam_confs false \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true --check_degenerate true 

Evaluation

Evaluating the model on the CARLA dataset:

pytorch_propane sbevnet eval_iou    \
 --model_name sbevnet_model --network_name sbevnet \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test --dataset_type carla \
 --eval_batch_size 1 \
 --datapath "datasets/carla/dataset.json" \
 --load_checkpoint_path "sbevnet_weights/carla/carla_save_0" \
 --image_w 512 \
 --image_h 288 \
 --max_disp 64 \
 --n_hmap 100 \
 --xmin 1 \
 --xmax 39 \
 --ymin -19 \
 --ymax 19 \
 --cx 256 \
 --cy 144 \
 --f 179.2531 \
 --tx 0.2 \
 --camera_ext_x 0.9 \
 --camera_ext_y -0.1 \
 --fixed_cam_confs true \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true 

Evaluating the model on the KITTI dataset:

pytorch_propane sbevnet eval_iou    \
 --model_name sbevnet_model --network_name sbevnet  \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test --dataset_type kitti \
 --eval_batch_size 1 \
 --datapath "datasets/kitti/dataset.json" \
 --load_checkpoint_path "sbevnet_weights/kitti/kitti_save_0" \
 --image_w 640 \
 --image_h 256 \
 --max_disp 64 \
 --n_hmap 128 \
 --xmin 5.72 \
 --xmax 43.73 \
 --ymin -19 \
 --ymax 19 \
 --camera_ext_x 0 \
 --camera_ext_y 0 \
 --fixed_cam_confs false \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true 

Save Predictions

Save predictions of the model on the CARLA dataset:

pytorch_propane sbevnet save_preds    \
 --model_name sbevnet_model --network_name sbevnet \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test --output_dir "predictions/kitti" \
 --eval_batch_size 1 \
 --datapath "datasets/carla/dataset.json" \
 --load_checkpoint_path "sbevnet_weights/carla/carla_save_0" \
 --image_w 512 \
 --image_h 288 \
 --max_disp 64 \
 --n_hmap 100 \
 --xmin 1 \
 --xmax 39 \
 --ymin -19 \
 --ymax 19 \
 --cx 256 \
 --cy 144 \
 --f 179.2531 \
 --tx 0.2 \
 --camera_ext_x 0.9 \
 --camera_ext_y -0.1 \
 --fixed_cam_confs true \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true 

Save predictions of the model on the KITTI dataset:

pytorch_propane sbevnet save_preds    \
 --model_name sbevnet_model --network_name sbevnet  \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test --output_dir "predictions/kitti" \
 --eval_batch_size 1 \
 --datapath "datasets/kitti/dataset.json" \
 --load_checkpoint_path "sbevnet_weights/kitti/kitti_save_0" \
 --image_w 640 \
 --image_h 256 \
 --max_disp 64 \
 --n_hmap 128 \
 --xmin 5.72 \
 --xmax 43.73 \
 --ymin -19 \
 --ymax 19 \
 --camera_ext_x 0 \
 --camera_ext_y 0 \
 --fixed_cam_confs false \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true 
Owner
Divam Gupta
Graduate student at Carnegie Mellon University | Former Research Fellow at Microsoft Research
Divam Gupta
StyleGAN2-ADA - Official PyTorch implementation

Abstract: Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmenta

NVIDIA Research Projects 3.2k Dec 30, 2022
Colossal-AI: A Unified Deep Learning System for Large-Scale Parallel Training

ColossalAI An integrated large-scale model training system with efficient parallelization techniques Installation PyPI pip install colossalai Install

HPC-AI Tech 7.1k Jan 03, 2023
Original Implementation of Prompt Tuning from Lester, et al, 2021

Prompt Tuning This is the code to reproduce the experiments from the EMNLP 2021 paper "The Power of Scale for Parameter-Efficient Prompt Tuning" (Lest

Google Research 282 Dec 28, 2022
Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme (NeurIPS2021)

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme (NeurIPS2021) Overview Prerequisites Linux Pytho

Shaojie Li 34 Mar 31, 2022
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.

Documentation: https://mmgeneration.readthedocs.io/ Introduction English | 简体中文 MMGeneration is a powerful toolkit for generative models, especially f

OpenMMLab 1.3k Dec 29, 2022
(Preprint) Official PyTorch implementation of "How Do Vision Transformers Work?"

(Preprint) Official PyTorch implementation of "How Do Vision Transformers Work?"

xxxnell 656 Dec 30, 2022
Can we visualize a large scientific data set with a surrogate model? We're building a GAN for the Earth's Mantle Convection data set to see if we can!

EarthGAN - Earth Mantle Surrogate Modeling Can a surrogate model of the Earth’s Mantle Convection data set be built such that it can be readily run in

Tim 0 Dec 09, 2021
Tom-the-AI - A compound artificial intelligence software for Linux systems.

Tom the AI (version 0.82) WARNING: This software is not yet ready to use, I'm still setting up the GitHub repository. Should be ready in a few days. T

2 Apr 28, 2022
Code for KHGT model, AAAI2021

KHGT Code for KHGT accepted by AAAI2021 Please unzip the data files in Datasets/ first. To run KHGT on Yelp data, use python labcode_yelp.py For Movi

32 Nov 29, 2022
Material related to the Principles of Cloud Computing course.

CloudComputingCourse Material related to the Principles of Cloud Computing course. This repository comprises material that I use to teach my Principle

Aniruddha Gokhale 15 Dec 02, 2022
Session-aware Item-combination Recommendation with Transformer Network

Session-aware Item-combination Recommendation with Transformer Network 2nd place (0.39224) code and report for IEEE BigData Cup 2021 Track1 Report EDA

Tzu-Heng Lin 6 Mar 10, 2022
PyTorch framework for Deep Learning research and development.

Accelerated DL & RL PyTorch framework for Deep Learning research and development. It was developed with a focus on reproducibility, fast experimentati

Catalyst-Team 29 Jul 13, 2022
Code accompanying the paper Shared Independent Component Analysis for Multi-subject Neuroimaging

ShICA Code accompanying the paper Shared Independent Component Analysis for Multi-subject Neuroimaging Install Move into the ShICA directory cd ShICA

8 Nov 07, 2022
[ICLR 2021, Spotlight] Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks, ICLR 2021 (Spotlight) Demo | Paper [NEW!] Time to play with our interac

Shengyu Zhao 373 Jan 02, 2023
Repo for Photon-Starved Scene Inference using Single Photon Cameras, ICCV 2021

Photon-Starved Scene Inference using Single Photon Cameras ICCV 2021 Arxiv Project Video Bhavya Goyal, Mohit Gupta University of Wisconsin-Madison Abs

Bhavya Goyal 5 Nov 15, 2022
RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection

RODD Official Implementation of 2022 CVPRW Paper RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection Introduction: Recent studie

Umar Khalid 17 Oct 11, 2022
PyExplainer: A Local Rule-Based Model-Agnostic Technique (Explainable AI)

PyExplainer PyExplainer is a local rule-based model-agnostic technique for generating explanations (i.e., why a commit is predicted as defective) of J

AI Wizards for Software Management (AWSM) Research Group 14 Nov 13, 2022
Mail classification with tensorflow and MS Exchange Server (ham or spam).

Mail classification with tensorflow and MS Exchange Server (ham or spam).

Metin Karatas 1 Sep 11, 2021
This is a Pytorch implementation of paper: DropEdge: Towards Deep Graph Convolutional Networks on Node Classification

DropEdge: Towards Deep Graph Convolutional Networks on Node Classification This is a Pytorch implementation of paper: DropEdge: Towards Deep Graph Con

401 Dec 16, 2022
Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception, IROS 2021

For academic use only. Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception Ziwei Wang, Liyuan Pan, Yonhon Ng, Zheyu Zhuang and Robert Mahony Th

Ziwei Wang 11 Jan 04, 2023