add rtdetr final #8094
Merged
add rtdetr final #8094
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Collaborator
lyuwenyu
commented
Apr 18, 2023
lyuwenyu
commented
- add pp rt-detr
add yoloe reader alter reference points to unsigmoid add 3_0_6_neck_256 base fix amp training alter usage in paddle-inference update new base alter ext_ops add hybrid encoder
|
Thanks for your contribution! |
RangeKing
reviewed
Apr 18, 2023
jerrywgz
reviewed
Apr 18, 2023
| value_spatial_shapes, | ||
| value_level_start_index, | ||
| value_mask=None): | ||
| """ |
|
|
||
|
|
||
| @register | ||
| class PPDETRTransformer(nn.Layer): |
| DETR: | ||
| backbone: ResNet | ||
| neck: HybridEncoder | ||
| transformer: PPDETRTransformer |
jerrywgz
reviewed
Apr 18, 2023
configs/rtdetr/README.md
Outdated
| # DETRs Beat YOLOs on Real-time Object Detection | ||
|
|
||
| ## Introduction | ||
| We propose a **R**eal-**T**ime **DE**tection **TR**ansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge. Specifically, we design an efficient hybrid encoder to efficiently process multi-scale features by decoupling the intra-scale interaction and cross-scale fusion, and propose IoU-aware query selection to improve the initialization of object queries. In addition, our proposed detector supports flexibly adjustment of the inference speed by using different decoder layers without the need for retraining, which facilitates the practical application of real-time object detectors. Our RT-DETR-L achieves 53.0% AP on COCO val2017 and 114 FPS on T4 GPU, while RT-DETR-X achieves 54.8% AP and 74 FPS, outperforming all YOLO detectors of the same scale in both speed and accuracy. Furthermore, our RT-DETR-R50 achieves 53.1% AP and 108 FPS, outperforming DINO-Deformable-DETR-R50 by 2.2% AP in accuracy and by about 21 times in FPS. |
lyuwenyu
force-pushed
the
rtdetr_final_L
branch
from
6fe61d6 to
df1c3e5
Compare
lyuwenyu
force-pushed
the
rtdetr_final_L
branch
from
df1c3e5 to
f742b70
Compare
nemonameless
approved these changes
Apr 18, 2023
jerrywgz
approved these changes
Apr 18, 2023
|
checkpoint、模型能转换成TRT engine么 |
Closed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.