Ryan Avery

Has anyone solved this issue? I am also getting this error. The LD_LIBRARY_PATH is incorrect in my TFServing container, using version 2.3. There is no nvidia folder ``` root@389958af6602:~# echo...

I tried exporting LD_LIBRARY_PATH like so ``` root@389958af6602:~# export LD_LIBRARY_PATH=/usr/local/cuda/extras/CUPTI/lib64 ``` since this folder contains libcupti.so.10.1 ``` root@389958af6602:~# ls /usr/local/cuda/extras/CUPTI/lib64 libcupti.so libcupti_static.a libnvperf_target.so libcupti.so.10.1 libnvperf_host.so libcupti.so.10.1.208 libnvperf_host_static.a ``` but when...

Any updates @minglotus-6 ? I tried this solution (see comment above) but it didn't work. https://github.com/tensorflow/tensorflow/issues/2626#issuecomment-261685470

Does this section of the docs need to be updated to reflect that you can't import from `ts` in the pytorch docker images? https://pytorch.org/serve/custom_service.html I'm trying to use a custom...

PIL is used in many ML frameworks for reading images, like [FastAI](https://www.fast.ai/) and [detectron2](https://github.com/facebookresearch/detectron2) and countless ML projects. When someone tries to use these frameworks or projects as examples with...

Also, I tried the following to install the kernelspec from within R, following instructions from https://github.com/IRkernel/IRkernel ``` source activate r-essentials R ``` then in the R terminal ``` install.packages('IRkernel') IRkernel::installspec()...

**update** After removing kernelspecs for python and r, which were in swapped locations (I want the r kernel to be in my r environment and python in base environment), I...

I'm getting this error ``` FROM pytorch/torchserve:0.5.3-cpu RUN pip install opencv-python ``` then `docker build -t cv2-torchserve:0.5.3-cpu .`

solved by https://github.com/pytorch/serve/issues/1499

Correct, we are working on it! So far I've been primarily focused on the ML Model extension, and Francis has been supporting this and improving ML AOI. We've discussed tackling...