-
python train.py
--hiera_path "/root/sam2-unet-main/sam2_hiera_large.pt"
--train_image_path "/root/autodl-tmp/DUTS-TR/DUTS-TR-Image/"
--train_mask_path "/root//autodl-tmp/DUTS-TR/DUTS-TR-Mask/"
--s…
-
https://github.com/facebookresearch/sam2
-
I encountered an issue while training the 2D case on Google Colab. Here's the error message:
`/content/Medical-SAM2/sam2_train/modeling/sam/transformer.py:22: UserWarning: Flash Attention…
-
Hi,
Is it possible to prompt like
text="car. road."
in this way?
TIA
-
python infer_video_tiny_debug.py --img_path 'img_data.npz' --gts_path X --propagate N --checkpoint tiny
When I'm running this it reply:
python infer_video_tiny_debug.py --img_path 'img_data.npz' -…
-
Hi,
Thank you for the excellent code.
I would like to know if incremental training is possible with SAM2-Unet.
I tried using the checkpoint 'SAM2-UNet-xx.pth' as input for 'hiera_path' in the …
-
When I tried to integrate sam2 into another model and initialize the sam2 model within the initialization function of the model class, I encountered the following error.
` def __init__(self, confi…
-
Hi,
I ran the sam2-demo on Ubuntu 24.04 LTS with Docker, and it works perfectly fine.
However, when I run the sam2-demo and download the segmented video, the file's FPS is set to 90,000, and the…
-
## タイトル: SAM2と動画カモフラージュ物体セグメンテーションの出会い：包括的な評価と適応
## リンク: https://arxiv.org/abs/2409.18653
## 概要:
本研究では、動画中のカモフラージュされたオブジェクトのセグメンテーション（VCOS）という困難なタスクにおける、Segment Anything Model 2（SAM2）の適用とパフォーマンスを調…
-
There is no sam2.1 model in Kijai/sam2-safetensors
Uniky updated
1 month ago