Kaggle Lyft Motion Prediction for Autonomous Vehicles 4th place solution

Overview

Lyft Motion Prediction for Autonomous Vehicles

Code for the 4th place solution of Lyft Motion Prediction for Autonomous Vehicles on Kaggle.

Directory structure

input               --- Please locate data here
src
|-ensemble          --- For 4. Ensemble scripts
|-lib               --- Library codes
|-modeling          --- For 1. training, 2. prediction and 3. evaluation scripts
  |-results         --- Training, prediction and evaluation results will be stored here
README.md           --- This instruction file
requirements.txt    --- For python library versions

Hardware (The following specs were used to create the original solution)

  • Ubuntu 18.04 LTS
  • 32 CPUs
  • 128GB RAM
  • 8 x NVIDIA Tesla V100 GPUs

Software (python packages are detailed separately in requirements.txt):

Python 3.8.5 CUDA 10.1.243 cuddn 7.6.5 nvidia drivers v.55.23.0 -- Equivalent Dockerfile for the GPU installs: Use nvidia/cuda:10.1-cudnn7-devel-ubuntu18.04 as base image

Also, we installed OpenMPI==4.0.4 for running pytorch distributed training.

Python Library

Deep learning framework, base library

  • torch==1.6.0+cu101
  • torchvision==0.7.0
  • l5kit==1.1.0
  • cupy-cuda101==7.0.0
  • pytorch-ignite==0.4.1
  • pytorch-pfn-extras==0.3.1

CNN models

Data processing/augmentation

  • albumentations==0.4.3
  • scikit-learn==0.22.2.post1

We also installed apex https://github.com/nvidia/apex

Please refer requirements.txt for more details.

Environment Variable

We recommend to set following environment variables for better performance.

export MKL_NUM_THREADS=1
export OMP_NUM_THREADS=1
export NUMEXPR_NUM_THREADS=1

Data setup

Please download competition data:

For the lyft-motion-prediction-autonomous-vehicles dataset, extract them under input/lyft-motion-prediction-autonomous-vehicles directory.

For the lyft-full-training-set data which only contains train_full.zarr, please place it under input/lyft-motion-prediction-autonomous-vehicles/scenes as follows:

input
|-lyft-motion-prediction-autonomous-vehicles
  |-scenes
    |-train_full.zarr (Place here!)
    |-train.zarr
    |-validate.zarr
    |-test.zarr
    |-... (other data)
  |-... (other data)

Pipeline

Our submission pipeline consists of 1. Training, 2. Prediction, 3. Ensemble.

Training with training/validation dataset

The training script is located under src/modeling.

train_lyft.py is the training script and the training configuration is specified by flags yaml file.

[Note] If you want to run training from scratch, please remove results folder once. The training script tries to resume from results folder when resume_if_possible=True is set.

[Note] For the first time of training, it creates cache for training to run efficiently. This cache creation should be done in single process, so please try with the single GPU training until training loop starts. The cache is directly created under input directory.

Once the cache is created, we can run multi-GPU training using same train_lyft.py script, with mpiexec command.

$ cd src/modeling

# Single GPU training (Please run this for first time, for input data cache creation)
$ python train_lyft.py --yaml_filepath ./flags/20201104_cosine_aug.yaml

# Multi GPU training (-n 8 for 8 GPU training)
$ mpiexec -x MASTER_ADDR=localhost -x MASTER_PORT=8899 -n 8 \
  python train_lyft.py --yaml_filepath ./flags/20201104_cosine_aug.yaml

We have trained 9 different models for final submission. Each training configuration can be found in src/modeling/flags, and the training results are located in src/modeling/results.

Prediction for test dataset

predict_lyft.py under src/modeling executes the prediction for test data.

Specify out as trained directory, the script uses trained model of this directory to inference. Please set --convert_world_from_agent true after l5kit==1.1.0.

$ cd src/modeling
$ python predict_lyft.py --out results/20201104_cosine_aug --use_ema true --convert_world_from_agent true

Predicted results are stored under out directory. For example, results/20201104_cosine_aug/prediction_ema/submission.csv is created with above setting.

We executed this prediction for all 9 trained models. We can submit this submission.csv file as the single model prediction.

(Optional) Evaluation with validation dataset

eval_lyft.py under src/modeling executes the evaluation for validation data (chopped data).

python eval_lyft.py --out results/20201104_cosine_aug --use_ema true

The script shows validation error, which is useful for local evaluation of model performance.

Ensemble

Finally all trained models' predictions are ensembled using GMM fitting.

The ensemble script is located under src/ensemble.

# Please execute from root of this repository.
$ python src/ensemble/ensemble_test.py --yaml_filepath src/ensemble/flags/20201126_ensemble.yaml

The location of final ensembled submission.csv is specified in the yaml file. You can submit this submission.csv by uploading it as dataset, and submit via Kaggle kernel. Please follow Save your time, submit without kernel inference for the submission procedure.

Py-faster-rcnn - Faster R-CNN (Python implementation)

py-faster-rcnn has been deprecated. Please see Detectron, which includes an implementation of Mask R-CNN. Disclaimer The official Faster R-CNN code (w

Ross Girshick 7.8k Jan 03, 2023
Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Vision Transformer Pytorch reimplementation of Google's repository for the ViT model that was released with the paper An Image is Worth 16x16 Words: T

Eunkwang Jeon 1.4k Dec 28, 2022
This project contains an implemented version of Face Detection using OpenCV and Mediapipe. This is a code snippet and can be used in projects.

Live-Face-Detection Project Description: In this project, we will be using the live video feed from the camera to detect Faces. It will also detect so

Hassan Shahzad 3 Oct 02, 2021
DFM: A Performance Baseline for Deep Feature Matching

DFM: A Performance Baseline for Deep Feature Matching Python (Pytorch) and Matlab (MatConvNet) implementations of our paper DFM: A Performance Baselin

143 Jan 02, 2023
[AI6101] Introduction to AI & AI Ethics is a core course of MSAI, SCSE, NTU, Singapore

[AI6101] Introduction to AI & AI Ethics is a core course of MSAI, SCSE, NTU, Singapore. The repository corresponds to the AI6101 of Semester 1, AY2021-2022, starting from 08/2021. The instructors of

AccSrd 1 Sep 22, 2022
Implementation of the ivis algorithm as described in the paper Structure-preserving visualisation of high dimensional single-cell datasets.

Implementation of the ivis algorithm as described in the paper Structure-preserving visualisation of high dimensional single-cell datasets.

beringresearch 285 Jan 04, 2023
An easier way to build neural search on the cloud

An easier way to build neural search on the cloud Jina is a deep learning-powered search framework for building cross-/multi-modal search systems (e.g

Jina AI 17k Jan 02, 2023
Simple torch.nn.module implementation of Alias-Free-GAN style filter and resample

Alias-Free-Torch Simple torch module implementation of Alias-Free GAN. This repository including Alias-Free GAN style lowpass sinc filter @filter.py A

이준혁(Junhyeok Lee) 64 Dec 22, 2022
Disentangled Cycle Consistency for Highly-realistic Virtual Try-On, CVPR 2021

Disentangled Cycle Consistency for Highly-realistic Virtual Try-On, CVPR 2021 [WIP] The code for CVPR 2021 paper 'Disentangled Cycle Consistency for H

ChongjianGE 94 Dec 11, 2022
This repository contains codes of ICCV2021 paper: SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation

SO-Pose This repository contains codes of ICCV2021 paper: SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation This paper is basically an

shangbuhuan 52 Nov 25, 2022
Official Pytorch implementation for "End2End Occluded Face Recognition by Masking Corrupted Features, TPAMI 2021"

End2End Occluded Face Recognition by Masking Corrupted Features This is the Pytorch implementation of our TPAMI 2021 paper End2End Occluded Face Recog

Haibo Qiu 25 Oct 31, 2022
FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics

FusionNet_Pytorch FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics Requirements Pytorch 0.1.11 Pyt

Choi Gunho 102 Dec 13, 2022
code for Fast Point Cloud Registration with Optimal Transport

robot This is the repository for the paper "Accurate Point Cloud Registration with Robust Optimal Transport". We are in the process of refactoring the

28 Jan 04, 2023
load .txt to train YOLOX, same as Yolo others

YOLOX train your data you need generate data.txt like follow format (per line- one image). prepare one data.txt like this: img_path1 x1,y1,x2,y2,clas

LiMingf 18 Aug 18, 2022
Codeflare - Scale complex AI/ML pipelines anywhere

Scale complex AI/ML pipelines anywhere CodeFlare is a framework to simplify the integration, scaling and acceleration of complex multi-step analytics

CodeFlare 169 Nov 29, 2022
GANfolk: Using AI to create portraits of fictional people to sell as NFTs

GANfolk are AI-generated renderings of fictional people. Each image in the collection was created by a pair of Generative Adversarial Networks (GANs) with names and backstories also created with AI.

Robert A. Gonsalves 32 Dec 02, 2022
An open-access benchmark and toolbox for electricity price forecasting

epftoolbox The epftoolbox is the first open-access library for driving research in electricity price forecasting. Its main goal is to make available a

97 Dec 05, 2022
NuPIC Studio is an all­-in-­one tool that allows users create a HTM neural network from scratch

NuPIC Studio is an all­-in-­one tool that allows users create a HTM neural network from scratch, train it, collect statistics, and share it among the members of the community. It is not just a visual

HTM Community 93 Sep 30, 2022
Official Pytorch implementation of "Learning Debiased Representation via Disentangled Feature Augmentation (Neurips 2021, Oral)"

Learning Debiased Representation via Disentangled Feature Augmentation (Neurips 2021, Oral): Official Project Webpage This repository provides the off

Kakao Enterprise Corp. 68 Dec 17, 2022
Pytorch implementation of "M-LSD: Towards Light-weight and Real-time Line Segment Detection"

M-LSD: Towards Light-weight and Real-time Line Segment Detection Pytorch implementation of "M-LSD: Towards Light-weight and Real-time Line Segment Det

123 Jan 04, 2023