Module.load is giving error "CppException: false CHECK FAILED at aten/src/ATen/Functions.h "

[siju-samuel]

Need help
Module.load is giving error "CppException: false CHECK FAILED at aten/src/ATen/Functions.h "
What is the reason? Even i can reproduce this issue with simple convolution layer.

2019-12-30 08:51:20.487 28171-28328/org.pytorch.demo E/PyTorchDemo: Error during image analysis com.facebook.jni.CppException: false CHECK FAILED at aten/src/ATen/Functions.h (empty at aten/src/ATen/Functions.h:3535) (no backtrace available) at org.pytorch.Module$NativePeer.initHybrid(Native Method) at org.pytorch.Module$NativePeer.<init>(Module.java:70) at org.pytorch.Module.<init>(Module.java:25) at org.pytorch.Module.load(Module.java:21) at org.pytorch.demo.vision.ImageClassificationActivity.analyzeImage(ImageClassificationActivity.java:166) at org.pytorch.demo.vision.ImageClassificationActivity.analyzeImage(ImageClassificationActivity.java:31) at org.pytorch.demo.vision.AbstractCameraXActivity.lambda$setupCameraX$2$AbstractCameraXActivity(AbstractCameraXActivity.java:90) at org.pytorch.demo.vision.-$$Lambda$AbstractCameraXActivity$t0OjLr-l_M0-_0_dUqVE4yqEYnE.analyze(Unknown Source:2) at androidx.camera.core.ImageAnalysisAbstractAnalyzer.analyzeImage(ImageAnalysisAbstractAnalyzer.java:57) at androidx.camera.core.ImageAnalysisNonBlockingAnalyzer$1.run(ImageAnalysisNonBlockingAnalyzer.java:135) at android.os.Handler.handleCallback(Handler.java:907) at android.os.Handler.dispatchMessage(Handler.java:105) at android.os.Looper.loop(Looper.java:216) at android.os.HandlerThread.run(HandlerThread.java:65)

The compiled android module is attached below.

android_torch_test.zip

Script to reproduce this issue:

`
import torch
import torch.nn as nn
import torchvision
from torchsummary import summary

class MyBlock(nn.Module):
def init(self, ninput, noutput):
super().init()
self.conv = nn.Conv2d(ninput, noutput - ninput, (3, 3), stride=2, padding=1, bias=True)
def forward(self, input):
return self.conv(input)

model = MyBlock(3,16).cuda()
model.eval()

print("-----MODEL---------")
print(model)

example_input = torch.rand(1, 3, 512, 1024).cuda()
print("Input Shape = ", example_input.shape)
print("-----MODEL SUMMARY---------")
print(summary(model, example_input.shape[1:]))

traced_script_module = torch.jit.trace(model, example_input)
traced_script_module.save("android_torch_test.pt")

`

Pytorch Version

I tried changing filenames of "android_torch_test.pt" to many, but upon Module.load, im getting model load error.
But if i load any models present in assets folder, its loading fine.