Issues
- 0
did anyone ever attach this to a language model?like mobilebert , use it to exactly segment the item we describe ,output the mask
#53 opened by arlisgreat - 1
- 1
Huggingface online demo does not work
#52 opened by burningsoulll - 1
Whether one data set is missing
#50 opened by kunpeng337 - 1
Can this be repeated? Can anyone replicate it?
#49 opened by kunpeng337 - 1
Release Timeline for RWKV-SAM Pretrained Model
#48 opened by Yaziwel - 4
Hugging Face Space link is invalid.
#47 opened by UQHTy - 2
running main.py occurs errors
#46 opened by zzk2021 - 1
Ovsam only can output one mask from one point?
#45 opened by kuiran - 1
About SAM datasets
#44 opened by jiugexuan - 1
how to inference on my custom data?
#43 opened by MargeryLab - 8
Where can I get the sam dataset
#31 opened by zxx0809 - 1
- 2
How $Q_{label}$ is updated?
#42 opened by lchen1019 - 3
- 0
- 3
- 1
about mmdet 2.0
#39 opened by jiuxuanth - 1
Evaluation scripts on LVIS dataset
#38 opened by Dyb3438 - 3
How can I evaluate on LVIS dataset?
#34 opened by Dyb3438 - 1
huggingface space failed
#36 opened by tanshuai0219 - 1
Prompt compare SAM
#35 opened by Danbinabo - 8
Could you provide a detailed environment configuration example?Does cuda have to be 12.1?
#32 opened by zxx0809 - 7
Can not open online demo
#20 opened by BboyHanat - 2
- 7
Problem regarding to creating the environment
#26 opened by EricLabile - 7
hao to Inference self datasts
#30 opened by Danbinabo - 0
- 3
- 1
- 2
How to use demo offline?
#25 opened by yepengxj - 2
Does it support full segmentation like SAM?
#24 opened by Atumyugi - 6
FileNotFoundError
#5 opened by CVHub520 - 2
- 2
How to add prompt?
#22 opened by hahapt - 1
Object level masks
#21 opened by mariiak2021 - 1
about "Feature-Crop baseline"
#17 opened by nhw649 - 1
Reduce Train Batch Size
#19 opened by WuHenry-0609 - 1
- 1
FileNotFoundError: [Errno 2] No such file or directory: '/usr/local/.cache/embd/RN50x16_CocoOVDataset.pth'
#16 opened by WuHenry-0609 - 1
text embedding
#15 opened by JIaqiYang78 - 1
- 1
Does OV-SAM support segment anything mode?
#13 opened by whu-pzhang - 3
How to recognize 22,000 classes?
#12 opened by David-19940718 - 3
Why don't you use clip-ViT as the backbone?
#11 opened by NeilHnxTcc - 1
Label token is useless?
#10 opened by jameslahm - 6
how to predict iou in ovsam?
#9 opened by yajieC - 2
segmentation for sky is error
#6 opened by chaoer - 2
Something wrong with the Ilustration?
#7 opened by ArsenLuca - 5
Missing ovsam.py File - Upload Inquiry
#3 opened by CVHub520