Comments (5)
pkgoogle
commented on May 3, 2024
Hi @dorishyc3, can you please share whether you have an M series or an intel chip for your Mac? Thanks.
from tensorflow.
dorishyc3
commented on May 3, 2024
Hello,
Iām using an M1 mac
from tensorflow.
pkgoogle
commented on May 3, 2024
Hi @dorishyc3, which version of the NDK are you using? Thanks.
from tensorflow.
dorishyc3
commented on May 3, 2024
my ndk version is 26
from tensorflow.
pkgoogle
commented on May 3, 2024
I'm running into a different issue, I tried with ndk version = 26 and 25b and the errors were similar but not exactly the same.
My reproduce step (on MacOS M1 and ndk=25b):
git clone https://github.com/tensorflow/tensorflow.git tensorflow_src
cd tensorflow_src
git switch r2.16
git pull
cd ..
mkdir tflite_build
cd tflite_build
cmake -DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK/build/cmake/android.toolchain.cmake -DANDROID_ABI=arm64-v8a -DTFLITE_ENABLE_GPU=ON -DBUILD_SHARED_LIBS=ON ../tensorflow_src/tensorflow/lite # This seems to work fine
cmake --build . -j # where it failsEnd of my output:
[ 48%] Linking CXX static library libruy_thread_pool.a
[ 48%] Built target ruy_profiler_profiler
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/qs8-vhswish/gen/qs8-vhswish-scalar-u2.c.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/qs8-vcvt/gen/qs8-vcvt-neon-u16.c.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/f32-vbinary/gen/f32-vrdivc-scalar-u1.c.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/f32-dwconv/gen/f32-dwconv-8f8m9l1c1s1r-scalar-acc2.c.o
[ 48%] Linking CXX shared library libabsl_random_internal_randen_hwaes.so
[ 48%] Built target absl_cordz_functions
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/qs8-vlrelu/gen/qs8-vlrelu-neon-u32.c.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x4-minmax-scalar.c.o
[ 48%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_tune.dir/tune.cc.o
[ 48%] Building ASM object _deps/xnnpack-build/CMakeFiles/microkernels-prod.dir/src/qu8-gemm/gen/qu8-gemm-4x16-minmax-rndnu-asm-aarch64-neon-mlal-lane-cortex-a75.S.o
[ 48%] Built target absl_bad_any_cast_impl
[ 48%] Linking CXX static library libruy_block_map.a
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x4-relu-scalar.c.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/f32-f16-vcvt/gen/f32-f16-vcvt-neon-u24.c.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/qs8-dwconv/gen/qs8-dwconv-25p16c-minmax-rndnu-neon-mul8-ld64.c.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/f32-vbinary/gen/f32-vdiv-minmax-scalar-u2.c.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/math/gen/f32-tanh-scalar-expm1minus-rr2-p6h4ts-div.c.o
[ 48%] Built target absl_throw_delegate
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/f32-rminmax/gen/f32-rmin-neon-u16-acc4.c.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/math/gen/f32-tanh-scalar-expm1minus-rr1-lut16-p3h1ts-div.c.o
[ 48%] Linking CXX static library libruy_tune.a
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/f16-rminmax/gen/f16-rmin-scalar-u4-acc2.c.o
[ 48%] Built target absl_scoped_set_env
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/src/f32-vhswish/gen/f32-vhswish-scalar-u1.c.o
[ 48%] Built target ruy_prepacked_cache
[ 48%] Built target microkernels-prod
[ 48%] Built target ruy_thread_pool
[ 48%] Built target absl_bad_variant_access
[ 48%] Built target logging
[ 48%] Built target absl_bad_optional_access
[ 48%] Linking CXX shared library libabsl_base.so
[ 48%] Built target absl_random_internal_randen_hwaes
[ 48%] Built target ruy_allocator
[ 48%] Linking CXX shared library libabsl_debugging_internal.so
[ 48%] Built target ruy_tune
gmake[1]: *** [CMakeFiles/Makefile2:6772: _deps/xnnpack-build/CMakeFiles/microkernels-all.dir/all] Error 2
gmake[1]: *** Waiting for unfinished jobs....
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/hardware-config.dir/src/configs/hardware-config.c.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-1x8-aarch64-neonfma-cortex-a53.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-gemm/gen/f16-gemm-6x16-aarch64-neonfp16arith-cortex-a55r0.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-igemm/gen/f32-igemm-6x8-aarch64-neonfma-cortex-a53.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-igemm/gen/f16-igemm-6x16-aarch64-neonfp16arith-cortex-a55r0.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-igemm/gen/f16-igemm-6x16-aarch64-neonfp16arith-ld64.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-6x8-aarch64-neonfma-cortex-a55.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-igemm/gen/f32-igemm-4x8-aarch64-neonfma-cortex-a55.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-gemm/gen/f16-gemm-1x16-aarch64-neonfp16arith-ld64.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-6x8-aarch64-neonfma-ld128.cc.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/memory.dir/src/memory.c.o
[ 48%] Built target ruy_block_map
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/jit/aarch64-assembler.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-igemm/gen/f16-igemm-4x16-aarch64-neonfp16arith-ld64.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-igemm/gen/f32-igemm-1x8-aarch64-neonfma-cortex-a53.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-gemm/gen/f16-gemm-6x16-aarch64-neonfp16arith-ld64.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-igemm/gen/f16-igemm-6x16-aarch64-neonfp16arith-cortex-a55.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-igemm/gen/f32-igemm-4x8-aarch64-neonfma-ld128.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-6x8-aarch64-neonfma-cortex-a53.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-igemm/gen/f32-igemm-6x8-aarch64-neonfma-cortex-a75.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-igemm/gen/f32-igemm-6x8-aarch64-neonfma-ld128.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-4x8-aarch64-neonfma-cortex-a75.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-gemm/gen/f16-gemm-4x16-aarch64-neonfp16arith-ld64.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-igemm/gen/f16-igemm-1x16-aarch64-neonfp16arith-ld64.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-igemm/gen/f32-igemm-6x8-aarch64-neonfma-cortex-a55.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-4x8-aarch64-neonfma-cortex-a55.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-gemm/gen/f16-gemm-6x16-aarch64-neonfp16arith-cortex-a75.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-gemm/gen/f16-gemm-6x16-aarch64-neonfp16arith-cortex-a55.cc.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-4x8-aarch64-neonfma-cortex-a53.cc.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/operator-utils.dir/src/operator-utils.c.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/post-operation.dir/src/operators/post-operation.c.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/jit/aarch32-assembler.cc.o
[ 48%] Building C object _deps/xnnpack-build/CMakeFiles/mutex.dir/src/mutex.c.o
[ 48%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f16-igemm/gen/f16-igemm-6x16-aarch64-neonfp16arith-cortex-a75.cc.o
[ 48%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_pack_avx.dir/pack_avx.cc.o
[ 48%] Built target absl_base
[ 48%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_pack_avx2_fma.dir/pack_avx2_fma.cc.o
[ 49%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/jit/assembler.cc.o
[ 49%] Built target operator-utils
[ 49%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_kernel_avx.dir/kernel_avx.cc.o
[ 49%] Built target absl_debugging_internal
[ 49%] Built target mutex
[ 49%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-1x8-aarch64-neonfma-ld64.cc.o
[ 49%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_ctx.dir/ctx.cc.o
[ 49%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_kernel_avx512.dir/kernel_avx512.cc.o
[ 49%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-igemm/gen/f32-igemm-1x8-aarch64-neonfma-cortex-a75.cc.o
[ 49%] Building C object _deps/xnnpack-build/CMakeFiles/operator-run.dir/src/operator-run.c.o
[ 49%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-igemm/gen/f32-igemm-4x8-aarch64-neonfma-cortex-a53.cc.o
[ 49%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_pack_avx512.dir/pack_avx512.cc.o
[ 49%] Linking CXX static library libruy_pack_avx2_fma.a
[ 49%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_kernel_arm.dir/kernel_arm32.cc.o
[ 49%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-4x8-aarch64-neonfma-ld128.cc.o
[ 50%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_kernel_avx2_fma.dir/kernel_avx2_fma.cc.o
[ 50%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-6x8-aarch64-neonfma-cortex-a75.cc.o
[ 50%] Linking CXX static library libruy_kernel_avx.a
[ 50%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-igemm/gen/f32-igemm-4x8-aarch64-neonfma-cortex-a75.cc.o
[ 50%] Building CXX object _deps/abseil-cpp-build/absl/random/CMakeFiles/absl_random_internal_randen.dir/internal/randen.cc.o
[ 50%] Built target hardware-config
[ 50%] Built target memory
[ 50%] Built target post-operation
[ 50%] Linking CXX static library libruy_pack_avx512.a
[ 50%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_kernel_arm.dir/kernel_arm64.cc.o
[ 50%] Building CXX object _deps/ruy-build/ruy/CMakeFiles/ruy_pack_arm.dir/pack_arm.cc.o
[ 50%] Building CXX object _deps/xnnpack-build/CMakeFiles/jit.dir/src/f32-gemm/gen/f32-gemm-1x8-aarch64-neonfma-cortex-a75.cc.o
[ 50%] Linking CXX static library libruy_pack_avx.a
[ 50%] Built target ruy_pack_avx2_fma
[ 50%] Linking CXX static library libruy_kernel_arm.a
[ 50%] Linking CXX static library libruy_ctx.a
[ 50%] Linking CXX static library libruy_kernel_avx512.a
[ 50%] Built target ruy_kernel_avx
[ 50%] Linking CXX static library libruy_kernel_avx2_fma.a
[ 50%] Linking CXX shared library libabsl_random_internal_randen.so
[ 50%] Built target ruy_pack_avx512
[ 50%] Built target operator-run
[ 50%] Built target jit
[ 50%] Linking CXX static library libruy_pack_arm.a
[ 50%] Built target ruy_pack_avx
[ 50%] Built target ruy_kernel_arm
[ 50%] Built target absl_random_internal_randen
[ 50%] Built target ruy_ctx
[ 50%] Built target ruy_kernel_avx2_fma
[ 50%] Built target ruy_kernel_avx512
[ 50%] Built target ruy_pack_arm
gmake: *** [Makefile:136: all] Error 2Hi @terryheo, can you please take a look? Thanks.
from tensorflow.
Related Issues (20)
- TFLiteConverter produces model that doesn't conform to GPUv2 (TfLiteGpuDelegate Init: FULLY_CONNECTED: Amount of input channels should match weights width)
- TextVectorization does not convert Cyrillic characters to lowercase
- 2.12.0: memory leak in TFLite's tflite::Interpreter::Invoke() HOT 2
- GPUv2 numerical inaccuracy in simple Add + Mul
- tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used. HOT 1
- Aborted (core dumped) with `tf.raw_ops.CombinedNonMaxSuppression`
- Aborted (core dumped) with `tf.raw_ops.Dilation2DBackpropFilter`
- Aborted (core dumped) with `tf.raw_ops.FakeQuantWithMinMaxVarsPerChannelGradient` HOT 1
- Segmentation fault (core dumped) in `tf.raw_ops.FractionalMaxPoolGrad` HOT 1
- Aborted (core dumped) with `tf.raw_ops.LRNGrad`
- Aborted (core dumped) with `tf.raw_ops.LSTMBlockCell`
- Aborted (core dumped) with `tf.raw_ops.LSTMBlockCellGrad` HOT 1
- Check fail in `tf.raw_ops.MaxPoolGradWithArgmax` HOT 1
- Aborted (core dumped) in `tf.raw_ops.NearestNeighbors`
- Aborted (core dumped) in `tf.raw_ops.SparseBincount`
- Aborted (core dumped) in `TensorScatterOp` HOT 1
- Buffer size mismatch in tensorflow/lite/kernels/stablehlo_pad.cc
- libtensorflow-cpu-windows-x86_64-2.15.0
- Dataset sharding warning
- libhexagon_interface.so for non Android - eLinux platform
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
š Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ššš
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ā¤ļø Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tensorflow.