shimen

Results 5 comments of shimen

Error in CuDNN: CUDNN_STATUS_BAD_PARAM (cudnnSetConvolutionNdDescriptor)

same problem here

CUDNN_STATUS_NOT_SUPPORTED (cudnnSetConvolutionNdDescriptor) with lua 5.2

Same problem here `/ib/external/home/ilyas/torchTest/install/bin/luajit: ...lyas/torchTest/install/share/lua/5.1/threads/threads.lua:179: [thread 2 endcallback] ...lyas/torchTest/install/share/lua/5.1/threads/threads.lua:183: [thread 1 callback] ...e/ilyas/torchTest/install/share/lua/5.1/nn/Container.lua:67: In 14 module of nn.Sequential: In 3 module of nn.DepthConcat: In 2 module of nn.Sequential: ...ome/ilyas/torchTest/install/share/lua/5.1/cudnn/init.lua:162: Error...

Washed CASIA-webface data set identities

Any update on the labels for the CASIA-webface data set

[BUG] TensorRT optimised model is detecting less objects compared to pytorch model, most likely some difference in post processing.

@himansh1314 @irexyc @grimoire I had the same issue in mmdeploy 0.13. You are right this is wrong preprocessing conversion. This issue is with keep_ratio not converted correctly. This is a...

[BUG] TensorRT optimised model is detecting less objects compared to pytorch model, most likely some difference in post processing.

@RunningLeon @irexyc @grimoire Can you confirm there is a bug in 0.13. Please see my previous comment