Closed kylin773 closed 1 year ago
Same problem for me. Any help?
Same problem for me. Any help?
it's pity that I don't get any solution to solve this problem.
Hi @jiuqiant, Could you please look into this build/install docker issue. Is there any recent changes has been made?
there's a solution in https://github.com/google/mediapipe/issues/3697 , but it does not work for me.
@Maisteru,
We are upgrading the MediaPipe Legacy Solutions to new MediaPipe solutions However, the libraries, documentation, and source code for all the MediaPipe Legacy Solutions will continue to be available in our GitHub repository and through library distribution services, such as Maven and NPM.
You can continue to use those legacy solutions in your applications if you choose. Though, we would request you to check new MediaPipe solutions which can help you more easily build and customize ML solutions for your applications. These new solutions will provide a superset of capabilities available in the legacy solutions. Thank you!!
This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.
This issue was closed due to lack of activity after being marked stale for past 7 days.
there is the error
Use --sandbox_debug to see verbose messages from the sandbox and retain the sandbox build root for debugging&, const LhsScalar, const tflite::cpu_backend_gemm::MatrixParams&, const RhsSca
lar , const tflite::cpu_backend_gemm::MatrixParams&, DstScalar*, const tflite::cpu_backend_gemm::GemmParams<int, DstScalar, quantization_flavor>&, int, int) [w
ith LhsScalar = signed char; RhsScalar = signed char; DstScalar = signed char; tflite::cpu_backend_gemm::QuantizationFlavor quantization_flavor = (tflite::cpu_backend_gem
m::QuantizationFlavor)1]':
external/arm_neon_2_x86_sse/NEON_2_SSE.h:2290:30: error: selector must be an integer constant in the range 0..7
In file included from /usr/lib/gcc/x86_64-linux-gnu/8/include/pmmintrin.h:31,
from /usr/lib/gcc/x86_64-linux-gnu/8/include/tmmintrin.h:31,
from /usr/lib/gcc/x86_64-linux-gnu/8/include/smmintrin.h:32,
from external/gemmlowp/fixedpoint/./fixedpoint_sse.h:21,
from external/gemmlowp/fixedpoint/fixedpoint.h:907,
from external/org_tensorflow/tensorflow/lite/kernels/internal/common.h:27,
from external/org_tensorflow/tensorflow/lite/kernels/internal/reference/batch_matmul.h:21,
from external/org_tensorflow/tensorflow/lite/kernels/batch_matmul.cc:16:
external/arm_neon_2_x86_sse/NEON_2_SSE.h: In static member function 'static void tflite::cpu_backend_gemm::detail::CustomGemvImpl<LhsScalar, RhsScalar, int, DstScalar, qu antization_flavor>::Run(const tflite::cpu_backend_gemm::MatrixParams
define _MM_INSERT_EPI16 _mm_insert_epi16
external/arm_neon_2_x86_sse/NEON_2_SSE.h:9363:40: note: in expansion of macro '_MM_INSERT_EPI16'
define vld1q_lane_s16(ptr, vec, lane) _MM_INSERT_EPI16(vec, *(ptr), lane)
external/arm_neon_2_x86_sse/NEON_2_SSE.h:12084:12: note: in expansion of macro 'vld1q_lane_s16' return vld1q_lane_s16(&val, vec, lane);
bazel build -c opt --define MEDIAPIPE_DISABLE_GPU=1 mediapipe/examples/desktop/object_detection:object_detection_cpu