search

tranluan / Nonlinear_Face_3DMM

Source code for "Nonlinear 3D Face Morphable Model"
http://cvlab.cse.msu.edu/project-nonlinear-3dmm.html
Apache License 2.0
675 stars 123 forks source link

cuda_op_kernel_v2_sx224.cu.o file not found in directory #12

Open tklinterg opened 5 years ago

tklinterg commented 5 years ago

Hi, firstly - really interesting article! I'm receiving the same issue as @yyssmm . I'm currently trying to run this on a windows 10 system with bash installed on it. Would you have a clue on were to start looking for a potential error?

Thanks in advance.

_Originally posted by @tklinterg in https://github.com/tranluan/Nonlinear_Face_3DMM/issues/4#issuecomment-481969216_

nyp0x commented 5 years ago

You may want to a comment out #include of Eigen Tensor in cuda_op_kernel_v2_sz224.cu. However, testing the model gives the error in my case: InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op ZbufferTriV2Sz224 with these attrs. Registered devices: [CPU], Registered kernels: device=GPU Node: ZbufferTriV2Sz224_15 = ZbufferTriV2Sz224[](transpose_16, Const_3, Squeeze_31)

nyp0x commented 5 years ago

It works (Ubuntu 18.04 / CUDA 10 / tf 1.13.1). Regarding InvalidArgumentError: it was cpu-only tensorflow installed in my env. Having complete implementation would be cool though.

huyanfei-cqupt commented 4 years ago

You may want to a comment out #include of Eigen Tensor in cuda_op_kernel_v2_sz224.cu. However, testing the model gives the error in my case: InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op ZbufferTriV2Sz224 with these attrs. Registered devices: [CPU], Registered kernels: device=GPU Node: ZbufferTriV2Sz224_15 = ZbufferTriV2Sz224[](transpose_16, Const_3, Squeeze_31)

Hi, Did you solve this problem?@knma

Nancyhhh commented 4 years ago

I have the same problem with yours. Is there anyone who has saved the problem?Please send a message on this, many thanks!

HOMGH commented 4 years ago

It works (Ubuntu 18.04 / CUDA 10 / tf 1.13.1). Regarding InvalidArgumentError: it was cpu-only tensorflow installed in my env. Having complete implementation would be cool though.

Hi @knma Could you run the main code with this configuration? (ubuntu 18 , CUDA 10 and tensrflow 1.13?)