Matteo

icon company Università degli studi di Firenze icon location Florence icon location PhD. student at Florence University and fellow research in Deep Learning at MICC

Results 4 issues of Matteo

Problem EigenCAM for YOLO5

3 comment

Hi there! Hello everyone! I am trying to use grad-cam with Yolov5. I've done some experimenting and if I run the notebook using the default code found at https://jacobgil.github.io/pytorch-gradcam-book/EigenCAM%20for%20YOLO5.html everything...

Docker container of the cloned task crashes/stucks.

12 comment

Hello everyone, I installed clearml server and clearml agent locally with docker on a ubuntu linux system following the documentation guide. My problem is with the task clone after write...

how to build a LiLT RobertaXML model with LayoutLMv3 tokenizer

As title I want to understand how we can create LiLT RobertaXML model with LayoutLMv3 tokenizer. The version SCUT-DLVCLab/lilt-roberta-en-base uses a LayoutLMv3 tokenizer, but the version of SCUT-DLVCLab/lilt-infoxlm-base don't use...

Custom Implementation of Grad-CAM and Grad-CAM++ for YOLOv10

Hi, I want to implement Grad-cam and Grad-cam ++ for YoloV10. Since YOLOv8_Explainer (https://github.com/Spritan/YOLOv8_Explainer) doesn't work for YoloV10, I was thinking that I can write a custom implementation of Grad-cam...