Eun-Cheon Lim

icon indicating a website link http://javawide.com icon indicating an email [email protected]

icon company NeuroEars icon location Anyang, KR icon location * Former Postdoc at Postech, Hallym University, Harvard Medical School * Earned Ph.D at Max-Planck Institute for Developmental Biology & Tuebingen University

Results 4 comments of Eun-Cheon Lim

Setting up TensorFlow plugin "fused_bias_act.cu": Preprocessing... Failed!

@MoZhengyang If the above mentioned solution does not work, the problem could be caused by the GCC compilation option while generating the **so** library. The GCC version of greater than...

Compile issue - "No rule to make target"

May be `/lib/modules/$(uname -r)/build`. Although those lines seemed to be removed in Ubuntu 22.04 kernel version 6.5.0. Instead you could try something as follows: `export KBUILD_EXTMOD=$(pwd)` before running make.

[Question or BUG] ONNX Runtime CUDA Sessions in Unity Produce Empty Outputs When Running Multiple Models Sequentially on a Single Graphic Card

**With only the Face Detect model**(single CUDA session on a GPU device): [FaceDetect.PostProcess] Output classificator[0]: 896, Output_regrssor: 14336, Thr: 0.6 [FaceDetect.NonMaxSuppression] # Original Faces: 5, # Filtered Faces: 1 **With...

[Question or BUG] ONNX Runtime CUDA Sessions in Unity Produce Empty Outputs When Running Multiple Models Sequentially on a Single Graphic Card

I have dropped to use the onnxruntime in my current project. Instead, I now directly use nVidia TensorRT, which creates the other problems, but it is controllable.