ConditionalDETR icon indicating copy to clipboard operation
ConditionalDETR copied to clipboard

verified publisher icon Atten4Vis
→

Metadata

This repository is an official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence". (https://arxiv.org/abs/2108.06152)

Results 11 ConditionalDETR issues
Sort by recently updated
recently updated
newest added

Improved efficiency in the forward part of the decoder.

https://github.com/Atten4Vis/ConditionalDETR/blob/8ea7c3f3fff49cd287855d4f13cc12a6066bc8e9/models/transformer.py#L145 Since `reference_points` does not change in the for loop, it is more efficient that pre-calculate the `obj_center`.

tyui592 avatar tyui592

← Metadata

345
Stars
46
Forks
Watchers

Owner

verified publisher icon Atten4Vis

Metadata

This repository is an official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence". (https://arxiv.org/abs/2108.06152)

Back