Questions about using TransXNet

[WatermelonFishhhhhhh]

Hi Lou,

   Thanks for your marvelous work TransXNet!
   Recently I am trying to use TransXNet as the encoder to do some dense prediction tasks, I simply do

   **model = TransXNet() or model = transxnet_t()** 

   Then it goes like this

   **TypeError: GELU: __init__() got an unexpected keyword argument 'inplace'**
   
   I am wondering whether this error is related to the version of mmcv.
   Could you tell me how to correctly use TransXNet or kindly provide the requirements.txt ?
   Thanks for your generous reply. :)

[Meng Lou]

Hi, thanks for your attention, please change the version of mmcv to 1.7.1 and try again.

…

---- Replied Message ---- | From | ***@***.***> | | Date | 11/22/2023 09:36 | | To | LMMMEng/TransXNet ***@***.***> | | Cc | Subscribed ***@***.***> | | Subject | [LMMMEng/TransXNet] Questions about using TransXNet (Issue #6) | Hi Lou, Thanks for your marvelous work TransXNet! Recently I am trying to use TransXNet as the encoder to do some dense prediction tasks, I simply do **model = TransXNet() or model = transxnet_t()** Then it goes like this **TypeError: GELU: __init__() got an unexpected keyword argument 'inplace'** I am wondering whether this error is related to the version of mmcv. Could you tell me how to correctly use TransXNet or kindly provide the requirements.txt ? Thanks for your generous reply. :) — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[WatermelonFishhhhhhh]

Hi, sorry for the late response, I have already change the mmcv version from the 1.4.3 to 1.7.1, the problem has been solved.
Thanks! :)