wangsssky / sonarsam Goto Github PK

Thanks for the great work. Do you have plans to release the inference code?

Reference: https://github.com/ChaoningZhang/MobileSAM

Our project performs on par with the original SAM and keeps exactly the same pipeline as the original SAM except for a change on the image encode, therefore, it is easy to Integrate into any project.

MobileSAM is around 60 times smaller and around 50 times faster than original SAM, and it is around 7 times smaller and around 5 times faster than the concurrent FastSAM. The comparison of the whole pipeline is summarzed as follows:

Best Wishes,

Qiao

Just acknowledged your effort to support MobileSAM in your project. Thanks~~

Thanks.

When using MobileSAM, only was modified SAM_ NAME and SAM_ CHECKPOINT, report the following error, do not understand the reason

  File "train_SAM.py", line 238, in <module>
    main()
  File "train_SAM.py", line 142, in main
    loss, outputs = net.forward(image, mask, boxes=boxes)
  File "/root/SonarSAM/model/model_proxy_SAM.py", line 377, in forward
    bce_loss = self.bcewithlogit(input=pred_masks, target=masks)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/loss.py", line 720, in forward
    return F.binary_cross_entropy_with_logits(input, target,
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/functional.py", line 3163, in binary_cross_entropy_with_logits
    raise ValueError("Target size ({}) must be the same as input size ({})".format(target.size(), input.size()))
ValueError: Target size (torch.Size([4, 12, 1024, 1024])) must be the same as input size (torch.Size([4, 3, 1024, 1024]))

when i use torch2.0 + torchvision0.15 , it makes "get wa unable to find engine to excute this computation"
when i use torch1.13 + torchvision0.14 , some api can not work because of transformerv2

Thanks for the cool work! Would you be able to make the SonarSAM model you trained available for download?

Hello, I encountered an error when attempting to fine-tune SonarSAM using box prompts. I followed your guidelines precisely while running the program. What could be the potential issues？