fatih akyon

cuda 11 support for docker

4

Hello thanks a lot for this great project! I want to upgrade the cuda support to 11 in the docker files. Is there anything i should consider while doing that...

Hello all! As far as I understood, it is not possible to perform real-time video classification using flash since it only supports prediction from folders/video files. If you guide me...

whats is NMM and IOS?

1

In the [paper](https://arxiv.org/abs/2202.06934) we only utilized standard NMS and IOU. The NMM and IOS will be discussed in a follow-up paper. For now you can consider NMM as non-maximum merging,...

List of Tutorials :100:

14

- [Introduction to SAHI](https://medium.com/codable/sahi-a-vision-library-for-performing-sliced-inference-on-large-images-small-objects-c8b086af3b80) - [Official paper](https://arxiv.org/abs/2202.06934) (NEW) - [Video inference support is live](https://github.com/obss/sahi/issues/457) (NEW) - [Kaggle notebook](https://www.kaggle.com/remekkinas/sahi-slicing-aided-hyper-inference-yv5-and-yx) - [Satellite object detection](https://blog.ml6.eu/how-to-detect-small-objects-in-very-large-images-70234bab0f98) - [Error analysis plots & evaluation](https://github.com/obss/sahi/issues/356) - [Interactive...

automatically check if SAHI version is up-to-date similar to https://github.com/layerai/sdk/pull/165

Video inference support is live :rocket:

5

Thanks to @madenburak, starting from v0.9.3, `sahi` brings full support for sliced/standard inference for video input format for all MMDetection/Detectron2/YOLOv5 models :fire:  - Just give video file as source:...

refactor demo notebooks by utilizing newly introduced AutoDetectionModel

5

https://github.com/obss/sahi/blob/main/demo/inference_for_detectron2.ipynb https://github.com/obss/sahi/blob/main/demo/inference_for_yolov5.ipynb https://github.com/obss/sahi/blob/main/demo/inference_for_mmdetection.ipynb https://github.com/obss/sahi/blob/main/demo/inference_for_huggingface.ipynb Instead of: ```python from sahi.models import Yolov5DetectionModel # load yolov5 models detection_model = Yolov5DetectionModel( model_path='yolov5s.pt', image_size=640, ) ``` Replace with this: ```python from sahi import AutoDetectionModel...

using yolov5 models from [this project](https://app.layer.ai/layer/yolov5-object-detection?tab=assets) or [that project](https://app.layer.ai/layer/yolov5) ```python from sahi import AutoDetectionModel detection_model = AutoDetectionModel.from_layer("layer/yolov5/models/yolov5s") ```

✔️ Install sahi: ```bash pip install -U sahi ``` ✔️ Create COCO formatted prediction results using COCO formatted dataset:  ```bash sahi predict --source image_dir/ --dataset_json_path dataset.json --model_type mmdet --model_path...

✔️ Install sahi: ```bash pip install -U sahi ``` ✔️ Install fiftyone: ```bash pip install -U fiftyone ``` ✔️ Start a fiftyone web app with your predictions results:  ```bash...