SAM-Adapter-PyTorch

SAM-Adapter-PyTorch copied to clipboard

How do I train with a single multi-card?

2

demoyu123

!torchrun train.py --config configs/demo.yaml may perform faster

8

Hello authors, Thanks so much for sharing these codes. The codes are very useful to fine-tune SAM for downstream works : ) I reduced datasize, adapted the codes and run...

YunyaGaoTree

i found validation results is different with test results, when you are training , when you utlize multi-GPU ddp. is any one same as me?

pingdanrensheng321

About ViT-B pre-trained model for COD task

1

Hello, we recently want to compare our work with your excellent work. Could you please give me a ViT-B pretrained model for COD task? Thank you very much

Sssssuperior

train not succeed

16

> size mismatch for image_encoder.blocks.23.mlp.lin1.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([5120, 1280]). size mismatch for image_encoder.blocks.23.mlp.lin1.bias: copying a param with...

skycat88

when I use the model I trained , the cuda will out of memory, but if I use the pretained model it`s fine

3

Hi , I have some problem when I try to use the model I trained. The first question is that , I use the config of vit-h and my GPU...

shhjjj

ERROR: Cannot install -r requirements.txt (line 1), -r requirements.txt (line 14), -r requirements.txt (line 15), -r requirements.txt (line 4), -r requirements.txt (line 6), -r requirements.txt (line 7) and numpy~=1.20.3 because...

AwayFromKeyboardwarrior

您好， 数据标准化的方法，即yaml文件里的data_norm的sub和div什么意思？谢谢回答。

CStar-777

I would like to ask how the comparative experiment "SAM" in the paper is operated, because the SAM source code will segment all objects (such as trees and houses next...

lixhere

Bug on evaluation during training

4

@tianrun-chen In func eval_psnr(),`pred_list = torch.cat(pred_list, 1) gt_list = torch.cat(gt_list, 1)` should be `pred_list = torch.cat(pred_list, 0) gt_list = torch.cat(gt_list, 0)`

TengliEd