Simone Riggi

I am trying to detect features in an astronomical image but I always get predicted bounding boxes that are always squared and with size 16x16 pixels (related to the rpn_stride??)....

Continue fine-tuning from previously trained model: error on inference

8

Dear all, I have fine-tuned TinyLLaVA-Phi-2-SigLIP-3.1B for 1 epoch and then continued the fine-tuning for another epoch starting from trained models saved after the first epoch. Both training runs were...

Dear all, I would like to extract the features (representation vector) of an input image from the pretrained SigLIP vision model. I tried the following, but I don't think this...

Dear all, I have fine-tuned a LLaVA-OneVision (0.5B and 7B) with LLM and vision components frozen. The checkpoint output directory contains these files: ``` runs checkpoint-1000 ... ... checkpoint-22000 trainer_state.json...

No object detected in inference after fine-tuning on custom dataset

5

Dear all, I am fine-tuning SAM3 on a custom astronomical dataset formatted in a COCO format. The dataset contains 5 object classes (custom naming), segmentation masks/bboxes and I have added...