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.

Simple tutorials on Pytorch DDP training

pytorch-distributed-training Distribute Dataparallel (DDP) Training on Pytorch Features Easy to study DDP training You can directly copy this code for

Ren Tianhe 188 Jan 06, 2023
Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm under Mixed Illumination

Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm under Mixed Illumination (ICCV 2021) Dataset License This work is l

DongYoung Kim 33 Jan 04, 2023
Job Assignment System by Real-time Emotion Detection

Emotion-Detection Job Assignment System by Real-time Emotion Detection Emotion is the essential role of facial expression and it could provide a lot o

1 Feb 08, 2022
PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

Poincaré Embeddings for Learning Hierarchical Representations PyTorch implementation of Poincaré Embeddings for Learning Hierarchical Representations

Facebook Research 1.6k Dec 25, 2022
基于Paddle框架的arcface复现

arcface-Paddle 基于Paddle框架的arcface复现 ArcFace-Paddle 本项目基于paddlepaddle框架复现ArcFace,并参加百度第三届论文复现赛,将在2021年5月15日比赛完后提供AIStudio链接~敬请期待 参考项目: InsightFace Padd

QuanHao Guo 16 Dec 15, 2022
10x faster matrix and vector operations

Bolt is an algorithm for compressing vectors of real-valued data and running mathematical operations directly on the compressed representations. If yo

2.3k Jan 09, 2023
Implementation of "With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition, BMVC, 2021" in PyTorch

Multimodal Temporal Context Network (MTCN) This repository implements the model proposed in the paper: Evangelos Kazakos, Jaesung Huh, Arsha Nagrani,

Evangelos Kazakos 13 Nov 24, 2022
Code release for "BoxeR: Box-Attention for 2D and 3D Transformers"

BoxeR By Duy-Kien Nguyen, Jihong Ju, Olaf Booij, Martin R. Oswald, Cees Snoek. This repository is an official implementation of the paper BoxeR: Box-A

Nguyen Duy Kien 111 Dec 07, 2022
Source code for "Progressive Transformers for End-to-End Sign Language Production" (ECCV 2020)

Progressive Transformers for End-to-End Sign Language Production Source code for "Progressive Transformers for End-to-End Sign Language Production" (B

58 Dec 21, 2022
InsightFace: 2D and 3D Face Analysis Project on MXNet and PyTorch

InsightFace: 2D and 3D Face Analysis Project on MXNet and PyTorch

Deep Insight 13.2k Jan 06, 2023
Video Corpus Moment Retrieval with Contrastive Learning (SIGIR 2021)

Video Corpus Moment Retrieval with Contrastive Learning PyTorch implementation for the paper "Video Corpus Moment Retrieval with Contrastive Learning"

ZHANG HAO 42 Dec 29, 2022
MemStream: Memory-Based Anomaly Detection in Multi-Aspect Streams with Concept Drift

MemStream Implementation of MemStream: Memory-Based Anomaly Detection in Multi-Aspect Streams with Concept Drift . Siddharth Bhatia, Arjit Jain, Shivi

Stream-AD 61 Dec 02, 2022
This is the pytorch implementation for the paper: Generalizable Mixed-Precision Quantization via Attribution Rank Preservation, which is accepted to ICCV2021.

GMPQ: Generalizable Mixed-Precision Quantization via Attribution Rank Preservation This is the pytorch implementation for the paper: Generalizable Mix

18 Sep 02, 2022
Blender Add-on that sets a Material's Base Color to one of Pantone's Colors of the Year

Blender PCOY (Pantone Color of the Year) MCMC (Mid-Century Modern Colors) HG71 (House & Garden Colors 1971) Blender Add-ons That Assign a Custom Color

Don Schnitzius 15 Nov 20, 2022
Learning Neural Network Subspaces

Learning Neural Network Subspaces Welcome to the codebase for Learning Neural Network Subspaces by Mitchell Wortsman, Maxwell Horton, Carlos Guestrin,

Apple 117 Nov 17, 2022
Wenzhou-Kean University AI-LAB

AI-LAB This is Wenzhou-Kean University AI-LAB. Our research interests are in Computer Vision and Natural Language Processing. Computer Vision Please g

WKU AI-LAB 10 May 05, 2022
Autonomous Robots Kalman Filters

Autonomous Robots Kalman Filters The Kalman Filter is an easy topic. However, ma

20 Jul 18, 2022
DeepLabv3+:Encoder-Decoder with Atrous Separable Convolution语义分割模型在tensorflow2当中的实现

DeepLabv3+:Encoder-Decoder with Atrous Separable Convolution语义分割模型在tensorflow2当中的实现 目录 性能情况 Performance 所需环境 Environment 注意事项 Attention 文件下载 Download

Bubbliiiing 31 Nov 25, 2022
traiNNer is an open source image and video restoration (super-resolution, denoising, deblurring and others) and image to image translation toolbox based on PyTorch.

traiNNer traiNNer is an open source image and video restoration (super-resolution, denoising, deblurring and others) and image to image translation to

202 Jan 04, 2023