FreddyGump

Pretrained weights

3

Did you pretrain the uniformer on any of the benchmark datasets? (Kinetics, something-something, ...) If you did, would you be able to share the state dicts? Thanks in advance!

How to generate visualizations of PAN

1

In the repository you show how PAN works for different actions (e.g. Yoyo). This is a very useful insight and I was wondering how I can generate similar visuals from...

yolo-v8 in onnx-runtime outperforms deepsparse on iMX8

2

**Describe the bug** I downloaded and tested the [yolov8-s-coco-pruned70_quantized](https://sparsezoo.neuralmagic.com/models/yolov8-s-coco-pruned70_quantized?hardware=deepsparse-c6i.12xlarge&comparison=yolov8-s-coco-base&tab=4) model from the sparseZoo. When I simply infere the onnx model with onnx-runtime, I get an average of 1,92 seconds (over...

ONNX conversion

4

Has anybody successfully converted the MTCNN to ONNX? Keep getting the error: ``` ~\Anaconda3\envs\facenet\lib\site-packages\facenet_pytorch\models\utils\detect_face.py in detect_face(imgs, minsize, pnet, rnet, onet, threshold, factor, device) 81 offset += boxes_scale.shape[0] 82 ---> 83...

quanto support for further model optimisation

2

### Search before asking - [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar feature requests. ### Description Huggingface recently released their `quanto` package. This is a toolkit...

Issue with building the GUI

1

Cannot build the GUI from the dockerfile: [WARNING]: Empty continuation line found in: RUN useradd -m $USERNAME && echo "$USERNAME:$USERNAME" | chpasswd && usermod --shell /bin/bash $USERNAME && usermod -aG...

Videos at 25fps tend to be choppy by default

8

I'm currently working on a project where I'm utilizing your method. I've observed that the method is configured to operate at 25 frames per second (fps), and I'm trying to...