The first thing to check is that you're using the latest nightly builds. Can you try manually clearing your gradle cache or change

implementation 'org.tensorflow:tensorflow-lite:0.0.0-nightly'
implementation 'org.tensorflow:tensorflow-lite-select-tf-ops:0.0.0-nightly'

to

implementation('org.tensorflow:tensorflow-lite:0.0.0-nightly') { changing = true }
implementation('org.tensorflow:tensorflow-lite-select-tf-ops:0.0.0-nightly') { changing = true }

?

Ok, I've tried switching to the "changing=true" syntax and rerunning, and after that I tried clearing the gradle cache (by removing ~/.gradle/caches) and I reran again. In both cases, the segfault was still there.

I see, thanks for checking. It's possible this is an emulator-specific issue. We'll take a look.

Ok, thanks! If there are any other checks I can do that would be helpful, I'm happy to give them a shot; just let me know.

If you can attach the logcat preceding the seg fault, that might be useful.

Ok, the logcat from the last run I did follows.

2020-03-31 14:31:28.646 18654-18654/? I/tflitebugrepor: Not late-enabling -Xcheck:jni (already on)
2020-03-31 14:31:28.659 18654-18654/? I/tflitebugrepor: Unquickening 13 vdex files!
2020-03-31 14:31:28.660 18654-18654/? W/tflitebugrepor: Unexpected CPU variant for X86 using defaults: x86
2020-03-31 14:31:28.894 18654-18654/com.example.tflitebugreport I/tflitebugrepor: The ClassLoaderContext is a special shared library.
2020-03-31 14:31:28.959 18654-18675/com.example.tflitebugreport I/ResourceExtractor: Found extracted resources res_timestamp-1-1585678399005
2020-03-31 14:31:29.007 18654-18678/com.example.tflitebugreport D/libEGL: loaded /vendor/lib/egl/libEGL_emulation.so
2020-03-31 14:31:29.008 18654-18678/com.example.tflitebugreport D/libEGL: loaded /vendor/lib/egl/libGLESv1_CM_emulation.so
2020-03-31 14:31:29.009 18654-18678/com.example.tflitebugreport D/libEGL: loaded /vendor/lib/egl/libGLESv2_emulation.so
2020-03-31 14:31:29.035 18654-18654/com.example.tflitebugreport D/HostConnection: HostConnection::get() New Host Connection established 0xe9c48910, tid 18654
2020-03-31 14:31:29.046 18654-18654/com.example.tflitebugreport D/HostConnection: HostComposition ext ANDROID_EMU_CHECKSUM_HELPER_v1 ANDROID_EMU_native_sync_v2 ANDROID_EMU_native_sync_v3 ANDROID_EMU_native_sync_v4 ANDROID_EMU_dma_v1 ANDROID_EMU_direct_mem ANDROID_EMU_host_composition_v1 ANDROID_EMU_host_composition_v2 ANDROID_EMU_vulkan ANDROID_EMU_deferred_vulkan_commands ANDROID_EMU_vulkan_null_optional_strings ANDROID_EMU_vulkan_create_resources_with_requirements ANDROID_EMU_YUV_Cache ANDROID_EMU_async_unmap_buffer ANDROID_EMU_vulkan_ignored_handles GL_OES_vertex_array_object GL_KHR_texture_compression_astc_ldr ANDROID_EMU_gles_max_version_2
2020-03-31 14:31:29.061 18654-18654/com.example.tflitebugreport D/EGL_emulation: eglCreateContext: 0xe9bd3280: maj 2 min 0 rcv 2
2020-03-31 14:31:29.143 18654-18681/com.example.tflitebugreport D/HostConnection: HostConnection::get() New Host Connection established 0xe9c48c80, tid 18681
2020-03-31 14:31:29.145 18654-18681/com.example.tflitebugreport D/HostConnection: HostComposition ext ANDROID_EMU_CHECKSUM_HELPER_v1 ANDROID_EMU_native_sync_v2 ANDROID_EMU_native_sync_v3 ANDROID_EMU_native_sync_v4 ANDROID_EMU_dma_v1 ANDROID_EMU_direct_mem ANDROID_EMU_host_composition_v1 ANDROID_EMU_host_composition_v2 ANDROID_EMU_vulkan ANDROID_EMU_deferred_vulkan_commands ANDROID_EMU_vulkan_null_optional_strings ANDROID_EMU_vulkan_create_resources_with_requirements ANDROID_EMU_YUV_Cache ANDROID_EMU_async_unmap_buffer ANDROID_EMU_vulkan_ignored_handles GL_OES_vertex_array_object GL_KHR_texture_compression_astc_ldr ANDROID_EMU_gles_max_version_2
2020-03-31 14:31:29.226 18654-18681/com.example.tflitebugreport D/EGL_emulation: eglMakeCurrent: 0xe9bd3280: ver 2 0 (tinfo 0xe7a8ea00)
2020-03-31 14:31:29.328 18654-18687/com.example.tflitebugreport I/flutter: Observatory listening on http://127.0.0.1:34829/x57mhTHSbR4=/
2020-03-31 14:31:29.448 18654-18654/com.example.tflitebugreport I/MainActivity: Made it here!
2020-03-31 14:31:29.498 18654-18654/com.example.tflitebugreport W/native: cpu_feature_guard.cc:36 The TensorFlow library was compiled to use SSE instructions, but these aren't available on your machine.
2020-03-31 14:31:29.498 18654-18654/com.example.tflitebugreport A/libc: Fatal signal 11 (SIGSEGV), code 1 (SEGV_MAPERR), fault addr 0xfffffff4 in tid 18654 (tflitebugreport), pid 18654 (tflitebugreport)

2020-03-31 14:31:29.498 18654-18654/com.example.tflitebugreport W/native: cpu_feature_guard.cc:36 The TensorFlow library was compiled to use SSE instructions, but these aren't available on your machine.

That looks potentially suspicious, though it doesn't immediately address the seg fault. It's very helpful though, we'll try to get back to you soon.

Thanks! I agree that the "SSE instructions" message does look suspicious.

One more observation, in case it helps: I notice that if I change the FlexDelegate to an NnApiDelegate, then I don't see a segfault, and I don't get the 'SSE instructions' message either.

I can reproduce the problem in my side as well. Will take a look for finding a root cause.

FYI, you can disable using SSE instructions by providing --copt="-mno-sse4" to the bazel build command.

I met the same problem:

A/libc: Fatal signal 11 (SIGSEGV), code 1 (SEGV_MAPERR), fault addr 0xfffffff4 in tid xxx (xxx), pid xxx (xxx)  

After build tensorflow without sse4.1 and sse4.2, it works!
My compiled tesroflow is available here https://github.com/fuzhenxin/Tensorflow-Lite-Select-TF-Ops-AAR

Is there any possibility this issue could be solved natively in tensorflow-lite? I'm also experiencing it when running an Android emulator.

Internal build script is updated.
I've verified with today's org.tensorflow:tensorflow-lite-select-tf-ops:0.0.0-nightly release.
Please let me know if you still have the issue. Thanks!

Are you satisfied with the resolution of your issue?
Yes
No

Looks like this works on my setup -- many thanks to all who helped!

This also worked for me.

If you're not familiar with gradle like myself, because the dependency version numbers are the same for every nightly build, you need to refresh your dependencies to get the latest nightly release.

Click Gradle (right-hand side of Android Studio), then Execute Gradle Task (the elephant icon), and enter gradle build --refresh-dependencies. This will re-download all your dependencies.

Has this issue returned for anyone else? I've done the above process to re-download dependencies, but my app has started crashing with the same segfault errors again.

build.gradle:

    implementation 'org.tensorflow:tensorflow-lite:0.0.0-nightly'
    implementation 'org.tensorflow:tensorflow-lite-select-tf-ops:0.0.0-nightly'
    implementation 'org.tensorflow:tensorflow-lite-support:0.0.0-nightly'

Crash:

W/native: cpu_feature_guard.cc:36 The TensorFlow library was compiled to use SSE instructions, but these aren't available on your machine.
A/libc: Fatal signal 11 (SIGSEGV), code 1 (SEGV_MAPERR), fault addr 0xfffffff4 in tid 32685 (init-21), pid 32643 (gdp19.truevoice)

@terryheo could you take a look at #38025 (comment) ?

I can verified the issue. Let me dig and prepare a fix.

The change was merged a week ago. But using nightly is still crashing since there is an issue of updating JCenter.
But you can use nightly directly from the Cloud Storage.
https://storage.googleapis.com/tensorflow-nightly-public/prod/tensorflow/google3/ubuntu_16/lite/nightly/511/20201214-223707/tensorflow-lite-select-tf-ops.aar

Hi There,

We are checking to see if you still need help on this issue, as you are using an older version of tensorflow(1.x) which is officially considered as end of life. We recommend that you upgrade to 2.4 or later version and let us know if the issue still persists in newer versions.

This issue will be closed automatically 7 days from now. If you still need help with this issue, Please open a new issue for any help you need against 2.x, and we will get you the right help.

Are you satisfied with the resolution of your issue?
Yes
No