3rd Place Solution of the Traffic4Cast Core Challenge @ NeurIPS 2021

Last update: Jul 25, 2022

Related tags

Deep Learning traffic4cast-2021

Overview

3rd Place Solution of Traffic4Cast 2021 Core Challenge

This is the code for our solution to the NeurIPS 2021 Traffic4Cast Core Challenge.

Paper

Our solution is described in the "Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation" paper.

If you wish to cite this code, please do it as follows:

@misc{konyakhin2021solving,
      title={Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation}, 
      author={Vsevolod Konyakhin and Nina Lukashina and Aleksei Shpilman},
      year={2021},
      eprint={2111.03421},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Competition and Demonstration Track @ NeurIPS 2021

Learnt parameters

The models' learnt parameters are available by the link: https://drive.google.com/file/d/1zD0CecX4P3v5ugxaHO2CQW9oX7_D4BCa/view?usp=sharing
Please download the archive and unzip it into the weights folder of the repository, so its structure looks like the following:

├── ...
├── traffic4cast
├── weights
│   ├── densenet                 
│   │   ├── BERLIN_1008_1430_densenet_unet_mse_best_val_loss_2019=78.4303.pth                     
│   │   ├── CHICAGO_1010_1730_densenet_unet_mse_best_val_loss_2019=41.1579.pth
│   │   └── MELBOURNE_1009_1619_densenet_unet_mse_best_val_loss_2019=25.7395.pth    
│   ├── effnetb5
│   │   ├── BERLIN_1008_1430_efficientnetb5_unet_mse_best_val_loss_2019=80.3510.pth    
│   │   ├── CHICAGO_1012_1035_efficientnetb5_unet_mse_best_val_loss_2019=41.6425.pth
│   │   ├── ISTANBUL_1012_2315_efficientnetb5_unet_mse_best_val_loss_2019=55.7918.pth    
│   │   └── MELBOURNE_1010_0058_efficientnetb5_unet_mse_best_val_loss_2019=26.0132.pth    
│   └── unet
│       ├── BERLIN_0806_1425_vanilla_unet_mse_best_val_loss_2019=0.0000_v5.pth    
│       ├── CHICAGO_0805_0038_vanilla_unet_mse_best_val_loss_2019=42.6634.pth
│       ├── ISTANBUL_0805_2317_vanilla_unet_mse_best_val_loss_2019=0.0000_v4.pth
│       └── MELBOURNE_0804_1942_vanilla_unet_mse_best_val_loss_2019=26.7588.pth
├── ...

Submission reproduction

To generate the submission file, please run the following script:

# $1 - absolute path to the dataset, $2 device to run inference
sh submission.sh {absolute path to dataset} {cpu, cuda}
# Launch example
sh submission.sh /root/data/traffic4cast cuda

The above sctipt generates the submission file submission/submission_all_unets_da_none_mpcpm1_mean_temporal_{date}.zip, which gave us the best MSE of 49.379068541527 on the final leaderboard.

3rd Place Solution of the Traffic4Cast Core Challenge @ NeurIPS 2021

Related tags

Overview

3rd Place Solution of Traffic4Cast 2021 Core Challenge

Paper

Learnt parameters

Submission reproduction

Owner

This is a collection of our NAS and Vision Transformer work.

functorch is a prototype of JAX-like composable function transforms for PyTorch.

Implementation for Stankevičiūtė et al. "Conformal time-series forecasting", NeurIPS 2021.

A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model

Selective Wavelet Attention Learning for Single Image Deraining

A new data augmentation method for extreme lighting conditions.

PyTorch implementation for COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction (CVPR 2021)

A Lightweight Hyperparameter Optimization Tool 🚀

2021搜狐校园文本匹配算法大赛分比我们低的都是帅哥队

DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates

UniFormer - official implementation of UniFormer

Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022)

Code base for the paper "Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation"

Examples of how to create colorful, annotated equations in Latex using Tikz.

Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

Accommodating supervised learning algorithms for the historical prices of the world's favorite cryptocurrency and boosting it through LightGBM.

CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

Code & Experiments for "LILA: Language-Informed Latent Actions" to be presented at the Conference on Robot Learning (CoRL) 2021.

git《Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction》(ECCV 2020) GitHub:

SE3 Pose Interp - Interpolate camera pose or trajectory in SE3, pose interpolation, trajectory interpolation

3rd Place Solution of the Traffic4Cast Core Challenge @ NeurIPS 2021

Related tags

Overview

3rd Place Solution of Traffic4Cast 2021 Core Challenge

Paper

Learnt parameters

Submission reproduction

Owner

This is a collection of our NAS and Vision Transformer work.

functorch is a prototype of JAX-like composable function transforms for PyTorch.

Implementation for Stankevičiūtė et al. "Conformal time-series forecasting", NeurIPS 2021.

A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model

Selective Wavelet Attention Learning for Single Image Deraining

A new data augmentation method for extreme lighting conditions.

PyTorch implementation for COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction (CVPR 2021)

A Lightweight Hyperparameter Optimization Tool 🚀

2021搜狐校园文本匹配算法大赛 分比我们低的都是帅哥队

DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates

UniFormer - official implementation of UniFormer

Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022)

Code base for the paper "Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation"

Examples of how to create colorful, annotated equations in Latex using Tikz.

Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

Accommodating supervised learning algorithms for the historical prices of the world's favorite cryptocurrency and boosting it through LightGBM.

CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

Code & Experiments for "LILA: Language-Informed Latent Actions" to be presented at the Conference on Robot Learning (CoRL) 2021.

git《Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction》(ECCV 2020) GitHub:

SE3 Pose Interp - Interpolate camera pose or trajectory in SE3, pose interpolation, trajectory interpolation

2021搜狐校园文本匹配算法大赛分比我们低的都是帅哥队