Qsingle/LearnablePromptSAM
Try to use the SAM-ViT as the backbone to create the learnable prompt for semantic segmentation
PythonApache-2.0
Issues
- 6
- 1
train on dataset iDRiD,iou is very small
#18 opened by liyan20180808 - 2
- 1
About one-shot and zero shot learning
#15 opened - 9
Is xFormers a must?
#14 opened by Heirudy - 3
GPU memory requirement
#13 opened by Raspberry-beans - 5
how is num_class decided?
#8 opened by krishnaadithya - 12
cuDNN error
#12 opened by liuyanice - 2
testing
#11 opened by FatimaaIsmail27 - 1
- 3
PromptSAM input Image_size
#9 opened by dxw2000 - 3
Video memory requirement
#1 opened by WusterHappy - 1
train_learnable_sam.py : TypeError: to() received an invalid combination of arguments - got (detype=torch.dtype, )
#7 opened by krishnaadithya - 2
num_class
#5 opened by xiaohongzaizhe - 2
environment configuration
#6 opened by yao-yu1999 - 1
"Prompt" is actually a adaptor
#4 opened by Luoxsh6 - 4
The important of num classes argument
#3 opened by thangngoc89 - 1
The role of variables in code
#2 opened by SZU-YoonAyU