SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.11250 · 2021

YOLOP: You Only Look Once for Panoptic Driving Perception

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 18 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
hustvl/yolop canonical 1 of 9
datvuthanh/HybridNets pwc_unofficial 8 of 9
FunctionStatusWhere it lives
calc_iou Ran datvuthanh/HybridNets/hybridnets/loss.py
code served (permissive licence) · get_code("9b3d320614140152")
check_anchor_order Ran datvuthanh/HybridNets/hybridnets/autoanchor.py
code served (permissive licence) · get_code("b1a13fb6db23f67f")
drop_connect Ran datvuthanh/HybridNets/hybridnets/model.py
code served (permissive licence) · get_code("2dd5dfa94542911e")
focal_loss_with_logits Ran datvuthanh/HybridNets/hybridnets/loss.py
code served (permissive licence) · get_code("edac15dd25a611c4")
get_same_padding_conv2d Ran datvuthanh/HybridNets/hybridnets/model.py
code served (permissive licence) · get_code("8e6b2e64bde860b4")
nms Ran datvuthanh/HybridNets/hybridnets/model.py
code served (permissive licence) · get_code("f35355d03c1b823d")
run_anchor Ran datvuthanh/HybridNets/hybridnets/autoanchor.py
code served (permissive licence) · get_code("6fa354b74082e9e8")
smooth_BCE Ran hustvl/yolop/lib/core/loss.py
code served (permissive licence) · get_code("386a04c4b6c96c88")
to_tensor Ran datvuthanh/HybridNets/hybridnets/loss.py
code served (permissive licence) · get_code("2ae72c2a3bc20ab4")
ap_per_class Not yet run hustvl/yolop/lib/core/evaluate.py
code served (permissive licence) · get_code("983459be55dc0e1c")
bbox_iou Not yet run hustvl/yolop/lib/core/general.py
code served (permissive licence) · get_code("8640c6fbdcca0d08")
box_iou Not yet run hustvl/yolop/lib/core/general.py
code served (permissive licence) · get_code("3113eedc8e71c19e")
compute_ap Not yet run hustvl/yolop/lib/core/evaluate.py
code served (permissive licence) · get_code("414621cded85ab0b")
connect_components_analysis Not yet run hustvl/yolop/lib/core/postprocess.py
code served (permissive licence) · get_code("aee2912ee8518d3e")
fitness Not yet run hustvl/yolop/lib/core/evaluate.py
code served (permissive licence) · get_code("b80233ae7b5070c8")
kmean_anchors Not yet run datvuthanh/HybridNets/hybridnets/autoanchor.py
code served (permissive licence) · get_code("47cc5eb0b9e95096")
morphological_process Not yet run hustvl/yolop/lib/core/postprocess.py
code served (permissive licence) · get_code("22bf9df8c2f70333")
non_max_suppression Not yet run hustvl/yolop/lib/core/general.py
code served (permissive licence) · get_code("ad8272beb4852755")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

A panoptic driving perception system is an essential part of autonomous driving. A high-precision and real-time perception system can assist the vehicle in making the reasonable decision while driving. We present a panoptic driving perception network (YOLOP) to perform traffic object detection, drivable area segmentation and lane detection simultaneously. It is composed of one encoder for feature extraction and three decoders to handle the specific tasks. Our model performs extremely well on the challenging BDD100K dataset, achieving state-of-the-art on all three tasks in terms of accuracy and speed. Besides, we verify the effectiveness of our multi-task learning model for joint training via ablative studies. To our best knowledge, this is the first work that can process these three visual perception tasks simultaneously in real-time on an embedded device Jetson TX2(23 FPS) and maintain excellent accuracy. To facilitate further research, the source codes and pre-trained models are released at https://github.com/hustvl/YOLOP.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2108.11250")
get_code_for_paper("2108.11250")
have("2108.11250")

Connect an agent — have() is free.