efficientdet-pytorch
efficientdet-pytorch copied to clipboard
rwightman
A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
Better but slowly NMS alternative: Code: https://github.com/ZFTurbo/Weighted-Boxes-Fusion Paper: https://arxiv.org/pdf/1910.13302.pdf It works for merging bboxes from one model too.
Based on: https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/86a370aa2cadea6ba7e5dffb2efc4bacc4c863ea/utils/box/box_utils.py#L47 Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression https://arxiv.org/pdf/1911.08287.pdf Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression https://giou.stanford.edu/GIoU.pdf UnitBox: An...
Just wanted to put this on the radar for the project - the developers of Complete IoU have extended it with clustered NMS: "...we propose Cluster-NMS, where NMS during inference...
Hi, I face an issue while trying to add backward hooks to a model that includes a BiFPN (to generate some gradient plots). I get the following error when calling...
**Is your feature request related to a problem? Please describe.** My model (both tf_efficientdet_d4 and tf_efficientdet_d7 is overfitting to a small dataset. I believe that freezing some of the layers...
**Describe the bug** Unable to save a model after successfully torch-scripting it. **To Reproduce** The following snippet: ``` from effdet import EfficientDet from effdet.config.model_config import get_efficientdet_config import torch architecture =...
Just wanted to drop this here in case somebody would be interested in tracking with these model 😄 https://github.com/mikel-brostrom/boxmot/blob/master/examples/efficient_det_boxmot.ipynb
**Is your feature request related to a problem? Please describe.** Python 3.11 is now on security status (https://devguide.python.org/versions/), but it's not supported on this package. **Describe the solution you'd like**...
Hello, I've got a working ONNX export thanks to tracing and `_batched_nms_coordinate_trick`. I've looked at previous issues and couldn't find a working ONNX export here or in any other pytorch...
