Horizon-Torch-Samples is an algorithm tool based on the Pytorch and Pytorch plugin interfaces, which is an efficient and user-friendly algorithm toolkit for Horizon BPUs.

PyTorch, on which Horizon-Torch-Samples relies, is a tensor library optimized for deep learning by using GPUs and CPUs, which is now one of the most popular deep learning frameworks. The Pytorch plugin is a set of quantization algorithm tools developed based on Pytorch. Focusing on the implementation of quantization functions close to the computing platform, its quantization algorithms are deeply coupled with Horizon computing platforms, and the quantization models trained with this tool can be compiled and run normally on Horizon BPUs.

As the basic framework of algorithm package developed by Horizon Robotics, Horizon-Torch-Samples is open to all algorithm users, developers, and researchers. Its quantization training is closely related to the Horizon processors and contains a complete process: Floating point training --> QAT training --> Fixed-point transformation prediction --> Model check compilation (for Horizon BPU) --> On-board accuracy simulation verification. It also provides state-of-the-art (SOTA) deep-learning models for common image tasks including classification, detection, segmentation, etc.

#Objectives

• Provide references for high-performance model architectures.
• Accelerate algorithm design and deliver production-ready solutions.
• Continuously iterate and update the latest algorithms.

#Features

• Based on Pytorch and horizon_plugin_pytorch.
• Include a complete process from Floating point training to On-board accuracy simulation verification.
• Include SOTA models for common image tasks such as classification, detection, and segmentation. All samples are compatible with Horizon BPUs.

#Sample Models

Horizon-Torch-Samples currently includes the following deep learning models:

Model Category	Model Name
Classification Model	resnet50_imagenet efficientnet_imagenet mixvargenet_imagenet henet_tinye_imagenet henet_tinym_imagenet
Detection model	fcos_efficientnetb3_mscoco deform_detr_resnet50_mscoco
Segmentation model	unet_mobilenetv1_cityscapes
3D Detection model	fcos3d_efficientnetb0_nuscenes
Bev Multi-task Model	bev_lss_efficientnetb0_multitask_nuscenes detr3d_efficientnetb3_nuscenes petr_efficientnetb3_nuscenes bevformer_tiny_resnet50_detection_nuscenes bev_sparse_henet_tinym_nuscenes bev_sparse_det_maptr_flashocc_henet_tinym_nuscenes
Online Map Construction	maptroe_henet_tinym_bevformer_nuscenes maptroe_sparse_henet_tinym_nuscenes
Occupancy Prediction Model	flashocc_henet_lss_occ3d_nuscenes
Multiple Object Track	motr_efficientnetb3_mot17
Trajectory Prediction Model	qcnet_oe_argoverse2
Lidar Detection Model	pointpillars_kitti_car centerpoint_pointpillar_nuscenes
Lidar Fusion Bev Multi-task Model	bevfusion_pointpillar_henet_multisensor_multitask_nuscenes bev_sparse_lidar_fusion_henet_tinym_nuscenes