[Feature]: Evaluation with TensorRT backend #5198
Merged
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Outdated suggestions cannot be applied.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.
This PR includes:
Results and Models
configs/fcos/fcos_r50_caffe_fpn_gn-head_4x4_1x_coco.py
configs/fsaf/fsaf_r50_fpn_1x_coco.py
configs/retinanet/retinanet_r50_fpn_1x_coco.py
configs/ssd/ssd300_coco.py
configs/yolo/yolov3_d53_mstrain-608_273e_coco.py
configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py
configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py
Notes:
All ONNX models are evaluated with dynamic shape on coco dataset and images are preprocessed according to the original config file.
Mask AP of Mask R-CNN drops by 1% for ONNXRuntime. The main reason is that the predicted masks are directly interpolated to original image in PyTorch, while they are at first interpolated to the preprocessed input image of the model and then to original image in other backend.
The performance drop for TensorRT is reasonable due to the detailed difference of
resize
op.