You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2021/10/26 02:40:38 UTC

[GitHub] [tvm] Kyrie-Zhao opened a new issue #9368: [Bug] A list of missing op conversion (Swin Transformer)

Kyrie-Zhao opened a new issue #9368:
URL: https://github.com/apache/tvm/issues/9368


   I am currently accelerating swin_transformer (ICCV2021 best paper)
   https://github.com/Kyrie-Zhao/Swin-Transformer/blob/main/models/swin_transformer.py
   
   which shows:
   
   NotImplementedError: The following operators are not implemented: **['aten::rand', 'aten::adaptive_avg_pool1d', 'aten::roll', 'aten::floor_']**
   
   BTW, anyone can provide some guidance regarding the procedure of implementing & registering an op by yourself? Appreciate it.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



[GitHub] [tvm] masahi commented on issue #9368: [Bug] A list of missing op conversion (Swin Transformer)

Posted by GitBox <gi...@apache.org>.
masahi commented on issue #9368:
URL: https://github.com/apache/tvm/issues/9368#issuecomment-951537701


   Can you show your script to trace the model? I got an error during tracing.
   
   
   
   > BTW, anyone can provide some guidance regarding the procedure of implementing & registering an op by yourself?
   
   By this, do you mean you want to work on this yourself, instead of asking us to do it?


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



[GitHub] [tvm] junrushao1994 closed issue #9368: [Bug] A list of missing op conversion (Swin Transformer)

Posted by GitBox <gi...@apache.org>.
junrushao1994 closed issue #9368:
URL: https://github.com/apache/tvm/issues/9368


   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



[GitHub] [tvm] Kyrie-Zhao commented on issue #9368: [Bug] A list of missing op conversion (Swin Transformer)

Posted by GitBox <gi...@apache.org>.
Kyrie-Zhao commented on issue #9368:
URL: https://github.com/apache/tvm/issues/9368#issuecomment-951619728


   > Can you show your script to trace the model? I got an error during tracing.
   > 
   > > BTW, anyone can provide some guidance regarding the procedure of implementing & registering an op by yourself?
   > 
   > By this, do you mean you want to work on this yourself, instead of asking us to do it?
   
   Here are the codes:
   ...
   from swin_transformer import SwinTransformer
   
   net = SwinTransformer()
   net = net.cuda()
   
   img = torch.randn(1, 3, 224, 224)
   device = torch.device("cuda")
   img = img.to(device)
   
   scripted_model = torch.jit.trace(net, img).eval()
   input_name = "swin_input"
   shape_list = [(input_name, img.shape)]
   swin_mod, swin_params = relay.frontend.from_pytorch(scripted_model, shape_list)
   
   _______
   Nah, I am just curious about the procedure of this implementation (to help me learn more about TVM). But the answer can be yes if it is not that complicated :D
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org