CODEWITHSUNDEEP
androidpytorch
geass_no_akuma
geass_no_akuma

Reputation: 11

Couldn't load the Pytorch optimised model in android

This is the error I'm getting in android while loading the model.

java.lang.RuntimeException: Unable to start activity ComponentInfo{com.android.example.cataractdetectionapp/com.android.example.cataractdetectionapp.InferenceActivity}: 

com.facebook.jni.CppException: Could not run 'aten::empty_strided' with arguments from the 'CUDA' backend.
This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). 
If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 

'aten::empty_strided' is only available for these backends: 
[CPU, Vulkan, BackendSelect, Python, Named, Conjugate, Negative, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, 
AutogradXLA, AutogradLazy, AutogradXPU, AutogradMLC, UNKNOWN_TENSOR_TYPE_ID, Autocast, Batched, VmapMode].

CPU: registered at aten/src/ATen/RegisterCPU.cpp:18433 [kernel]

Vulkan: registered at ../aten/src/ATen/native/vulkan/ops/Factory.cpp:47 [kernel]
BackendSelect: registered at aten/src/ATen/RegisterBackendSelect.cpp:665 [kernel]
Python: registered at ../aten/src/ATen/core/PythonFallbackKernel.cpp:47 [backend fallback]
Named: registered at ../aten/src/ATen/core/NamedRegistrations.cpp:7 [backend fallback]
Conjugate: fallthrough registered at ../aten/src/ATen/ConjugateFallback.cpp:22 [kernel]
Negative: fallthrough registered at ../aten/src/ATen/native/NegateFallback.cpp:22 [kernel]
ADInplaceOrView: fallthrough registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:64 [backend fallback]
AutogradOther: fallthrough registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:35 [backend fallback]
AutogradCPU: fallthrough registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:39 [backend fallback]
AutogradCUDA: fallthrough registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:47 [backend fallback]
AutogradXLA: fallthrough registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:51 [backend fallback]
AutogradLazy: fallthrough registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:55 [backend fallback]
AutogradXPU: fallthrough registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:43 [backend fallback]
AutogradMLC: fallthrough registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:59 [backend fallback]
UNKNOWN_TENSOR_TYPE_ID: fallthrough registered at ../aten/src/ATen/autocast_mode.cpp:466 [backend fallback]
Autocast: fallthrough registered at ../aten/src/ATen/autocast_mode.cpp:305 [backend fallback]
Batched: registered at ../aten/src/ATen/BatchingRegistrations.cpp:1016 [backend fallback]
VmapMode: fallthrough registered at ../aten/src/ATen/VmapModeRegistrations.cpp:33 [backend fallback]

I used the below code for loading the module:

Module module = LiteModuleLoader.load(assetFilePath(getApplicationContext(), "Model.ptl"));

The dependencies I'm using for Pytorch are as follows:

implementation 'org.pytorch:pytorch_android_lite:1.10.0'
implementation 'org.pytorch:pytorch_android_torchvision:1.10.0'

Upvotes: 0

Views: 1066

Answers (1)

geass_no_akuma
geass_no_akuma

Reputation: 11

The solution to this error was simple. The error was because the model was saved with the Runtime being GPU. So, I loaded the native PyTorch model again in the CPU environment and saved it for Lite Interpreter and it is successfully loading in the android app.

Upvotes: 1

Related Questions