ai.djl.engine.EngineException: Failed to load PyTorch native library

[Cyu1]

Caused by: java.lang.UnsatisfiedLinkError: C:\Users\80313223.djl.ai\pytorch\1.12.1-20220818-cpu-win-x86_64\asmjit.dll: Can't find dependent libraries ai.djl.engine.EngineException: Failed to load PyTorch native library

ai.djl.pytorch pytorch-jni 1.13.0-0.20.0 ai.djl.pytorch pytorch-native-cpu win-x86_64 runtime 1.13.0

[frankfliu]

1. Are you using DJL API 0.20.0 jar, can you share your pom.xml or build.gradle file?
2. Did you install VC++ redistribute package? See: https://docs.djl.ai/master/docs/development/troubleshooting.html#13-unsatisfiedlinkerror-issue
3. Can you run DJL examples on your machine?

[Cyu1]

1. 你在使用 DJL API 0.20.0 jar，你能分享你的 pom.xml 或 build.gradle 文件吗？
2. 您是否安装了 VC++ 重新分发包？请参阅：https ://docs.djl.ai/master/docs/development/troubleshooting.html#13-unsatisfiedlinkerror-issue
3. 你能在你的机器上运行 DJL 示例吗？

1、并没有安装vc++ 2、没有测试过在自己机器上运行DJL演示，主要是写的自己得代码 3、pom文件引入了djl以及相关得spark，除此之外就没有其他引入了

ai.djl.pytorch pytorch-jni ${pytorch.native.version}-${djl.version} ai.djl.pytorch pytorch-native-cpu ${pytorch.native.classifier} runtime ai.djl.pytorch pytorch-jni ${pytorch.native.version}-${djl.version} ai.djl.pytorch pytorch-native-cpu ${pytorch.native.classifier} runtime ${pytorch.native.version}

[Cyu1]

1. 你在使用 DJL API 0.20.0 jar，你能分享你的 pom.xml 或 build.gradle 文件吗？
2. 您是否安装了 VC++ 重新分发包？请参阅：https ://docs.djl.ai/master/docs/development/troubleshooting.html#13-unsatisfiedlinkerror-issue
3. 你能在你的机器上运行 DJL 示例吗？

但是当我使用eclipse运行，项目可以正常执行。当使用idea运行代码，就会出现 failed to load pytorch native library.

[ThiloteE]

Please try one of two solutions that worked in my particular case:

• A) Have no CUDA installed on your system (and have no CUDA paths set in your systems Environment Variables), then it hopefully will automatically detect the correct location of the CUDA path, if it is assume that it is managed by the DeepJavaLibrary and the system will also somehow find all dependencies.

• B) (If you have multiple CUDA installed on your system) Add C:\Users\USER\.djl.ai\pytorch\CUDA-VERSION (in my case it was C:\Users\USER\.djl.ai\pytorch\2.4.0-cu124-win-x86_64 to "PATH" in Windows 10 Environment Variables. Can be done via searching for environment variables and manually adding the folder path. See https://www.howtogeek.com/787217/how-to-edit-environment-variables-on-windows-10-or-11/

Links and comments that helped me find the answers:

• https://stackoverflow.com/questions/6092200/how-to-fix-an-unsatisfiedlinkerror-cant-find-dependent-libraries-in-a-jni-pro
• https://github.com/KernFerm/nvidia-installation-guide?tab=readme-ov-file#setting-up-cuda-118-with-cudnn-on-windows
• https://forum.image.sc/t/trouble-getting-gpu-to-work-with-instanseg-qupath/102042/22
• https://forum.image.sc/t/trouble-getting-gpu-to-work-with-instanseg-qupath/102042/26