Failed to load PyTorch native library in load_pytorch_model.ipynb

[melodrama04]

In djl.jupyter.load_pytorch_model.ipynb,when I am running " Criteria<Image, Classifications> criteria = Criteria.builder() .setTypes(Image.class, Classifications.class) .optModelPath(Paths.get("build/pytorch_models/resnet18")) .optOption("mapLocation", "false") // this model requires mapLocation for GPU .optTranslator(translator) .optProgress(new ProgressBar()).build();

ZooModel model = criteria.loadModel(); " it gets this information

"

ai.djl.engine.EngineException: Failed to load PyTorch native library at ai.djl.pytorch.engine.PtEngine.newInstance(PtEngine.java:90) at ai.djl.pytorch.engine.PtEngineProvider.getEngine(PtEngineProvider.java:40) at ai.djl.engine.Engine.getEngine(Engine.java:190) at ai.djl.Model.newInstance(Model.java:99) at ai.djl.repository.zoo.BaseModelLoader.createModel(BaseModelLoader.java:191) at ai.djl.repository.zoo.BaseModelLoader.loadModel(BaseModelLoader.java:154) at ai.djl.repository.zoo.Criteria.loadModel(Criteria.java:172) at .(#40:1) "

I didnt change code.

Environment Info

Engines --------------- DJL version: 0.24.0-SNAPSHOT [WARN ] - No matching cuda flavor for win found: cu120mkl/sm_61. [DEBUG] - Using cache dir: C:\Users\guest123.djl.ai\mxnet\1.9.1-mkl-win-x86_64 [INFO ] - Downloading libgcc_s_seh-1.dll ... [INFO ] - Downloading libgfortran-3.dll ... [INFO ] - Downloading libopenblas.dll ... [INFO ] - Downloading libquadmath-0.dll ... [INFO ] - Downloading mxnet.dll ... [DEBUG] - Loading mxnet library from: C:\Users\guest123.djl.ai\mxnet\1.9.1-mkl-win-x86_64\mxnet.dll [WARN ] - No matching cuda flavor for win found: cu120mkl/sm_61. Default Engine: MXNet:1.9.0, capabilities: [ SIGNAL_HANDLER, LAPACK, BLAS_OPEN, OPENMP, OPENCV, MKLDNN, ] MXNet Library: C:\Users\guest123.djl.ai\mxnet\1.9.1-mkl-win-x86_64\mxnet.dll Default Device: cpu() PyTorch: 2 MXNet: 0 XGBoost: 10 LightGBM: 10 OnnxRuntime: 10 TensorFlow: 3

[zachgk]

This is an issue accessing the pytorch binary code that our pytorch engine is built on. Are you import Pytorch at runtime as opposed to through a jar? If so, make sure the notebook can access ~/.djl.ai/pytorch where it will try to cache the native library. See if the file exist there.

Also, there should be another section to the error message

[melodrama04]

This is an issue accessing the pytorch binary code that our pytorch engine is built on. Are you import Pytorch at runtime as opposed to through a jar? If so, make sure the notebook can access ~/.djl.ai/pytorch where it will try to cache the native library. See if the file exist there.

Also, there should be another section to the error message

[melodrama04]

This is an issue accessing the pytorch binary code that our pytorch engine is built on. Are you import Pytorch at runtime as opposed to through a jar? If so, make sure the notebook can access ~/.djl.ai/pytorch where it will try to cache the native library. See if the file exist there.

Also, there should be another section to the error message

The file exits. And I can run the other notebook in this directory.The problem only happens when I try to run the pytorch one. Up above is all error message I got.