sam3

sam3 copied to clipboard

Pin to numpy 1.26.X not strictly 1.26

2

mlopezantequera

SAM3 video training config file

3

Hi, did anyone work around for video training? All of the config files for videos are intended for evaluation only, and I have figured out how to start training. However,...

machlovi

bpe_simple_vocab_16e6.txt.gz missing

4

Getting FileNotFound error when trying to load processor. For this file in particular "bpe_simple_vocab_16e6.txt.gz" This is my patch :P try: self.model = build_sam3_image_model() self.processor = Sam3Processor(self.model) except FileNotFoundError: response =...

lexhacke

Training Fails with AttributeError: 'list' object has no attribute 'popitem' on Custom COCO Dataset

1

I am trying to train **SAM3** on a custom segmentation dataset. The dataset was annotated using **CVAT** and exported in **COCO** format. After exporting, I updated the COCO annotations to...

wakasturner

Weird outputs for point prompts

8

I tried the SAM3 model for point prompts. When compared to SAM2, it produced such outputs frequently.

btbrandon

Reduced the resolution in the the hydra config from 1008, for fine-tuning, to avoid OOM error. Now I only get assertion errors.

2

I have reduced the resolution from 1008 to multiple choices, such as 512, 504, 490 and many more choices, but I keep getting errors The below is the traceback I...

BahMoh

Transfer concept from one image to another

25

Hi sam3 team, thanks for your awesome work! Is it possible to transfer the embedding learned from the bounding box of an object in one image to another image, in...

keejkrej

Sam 3 Segmentation Fine Tuning

5

Does sam3 not support segmentation fine tuning at this moment? When I use the following config: # @package _global_ defaults: - _self_ # ============================================================================ # Paths Configuration (Chage this to...

MohitDAngrish

Add the data serialization factor in COCO-JSON-LOADER

2

This is for the issue #307 . (Closes #307 ) When I finetuned the sam3 with a large dataset (like larger than 1M 2D images), I faced the memory leak...

yhy258

Memory Leakage Problem?

2

When I tried to fine-tune the model with a large annotation set (about 2M), memory usage gradually increased during the training process. Ultimately, the process was exploded.

yhy258