Yash Khurana
Yash Khurana
Hello big brother @hukaixuan19970627 , I'm currently trying to calculate csl labels using the function given by you gaussian_label_cpu. However, for large tensors of size >=20k the function seems very...
I understand that USI is used for training SOTA CNN models for ImageNet. I was wondering if there's any possibility if we could use it to train a model (ex:...
Hi, while evaluating the performance of the quantized v8 models I realized that the current exporting pipeline does something slightly different from how the models were actually exported for the...
Hello, I'm trying to train YOLOv8-large in int4 format. I took the training recipe available at [sparsezoo](https://sparsezoo.neuralmagic.com/models/yolov8-l-coco-pruned85_quantized?hardware=deepsparse-c4.8xlarge&comparison=yolov8-l-coco-base) for training yolov8-large. I modified the num_bits to 4 everywhere. I also saw...
### Search before asking - [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. ### Question Hello! I'm looking to extract features of individual...
Hi, I wanted to use the features of the predicted boxes for downstream tasks. I have tried using the features from the layer before the last 1x1 convolution. They are...
Hello, great work on improving the v8 family! I was trying to train YOLOv10m on the LVIS Dataset. While the dataset is quite complex and big, I'm barely able to...