High performance Cross-platform Inference-engine, you could run Anakin on x86-cpu,arm, nv-gpu, amd-gpu,bitmain and cambricon devices.
Home Page: https://anakin.baidu.com/
License: Apache License 2.0
based on ubuntu Dockerfile, and changed gcc version to 4.8.5.
error message as follows.
Linking CXX executable ../../output/unit_test/test_saber_buffer_NV
/usr/bin/ld: ../../output/libanakin.so.2.0.1: undefined reference to symbol 'cudnnGetRNNLinLayerBiasParams'
/usr/lib/gcc/x86_64-linux-gnu/4.8/../../../x86_64-linux-gnu/libcudnn.so: error adding symbols: DSO missing from command line
collect2: error: ld returned 1 exit status
test/CMakeFiles/test_TargetWrapper.dir/build.make:93: recipe for target '../output/unit_test/test_TargetWrapper' failed
make[2]: *** [../output/unit_test/test_TargetWrapper] Error 1
CMakeFiles/Makefile2:757: recipe for target 'test/CMakeFiles/test_TargetWrapper.dir/all' failed
make[1]: *** [test/CMakeFiles/test_TargetWrapper.dir/all] Error 2
no example for new user
https://github.com/PaddlePaddle/Anakin/blob/developing/benchmark/README_GPU.md
try to test: Vgg16
proto: from https://github.com/OpenHero/caffe/tree/dev
prototxt: from http://www.robots.ox.ac.uk/~vgg/research/very_deep/ | https://gist.github.com/ksimonyan/211839e770f7b538e2d8#file-readme-md
model: from http://www.robots.ox.ac.uk/~vgg/research/very_deep/ | https://gist.github.com/ksimonyan/211839e770f7b538e2d8#file-readme-md
macos, protobuf3.5
run python converter.py
generate error.
An extra null pointer check is not needed in functions like the following.
In file included from error/usr/include/c++/4.2.1/vector: :65:
In file included from /usr/include/c++/4.2.1/bits/functexcept.h:Unsupported41 :
architectureIn file included from /usr/include/c++/4.2.1/bits/c++config.h
:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:71:
In file included from /usr/include/_types.h:27:
In file included from /usr/include/sys/_types.h:32:
/usr/include/sys/cdefs.h#error Unsupported architecture:
763: ^2
: error: Unsupported architecture
#error Unsupported architecture
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/tensor_lite.h:19:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/shape_lite.h:17:
In file included from /usr/include/c++/4.2.1/vector:65:
In file included from /usr/include/c++/4.2.1/bits/functexcept.h:41:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.h:18:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/tensor_lite.h:19:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/shape_lite.h:17:
In file included from /usr/include/c++/4.2.1/vector:65:
In file included from /usr/include/c++/4.2.1/bits/functexcept.h:41:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:71:
In file included from /usr/include/_types.h:27:
In file included from /usr/include/sys/_types.h:33:
/usr/include/machine/_types.h:34:2: error: architecture not:
In file included from /usr/include/unistd.h:71:
In file included from /usr/include/_types.h:27:
In file included from /usr/include/sys/_types.h:33:
/usr/include/machine/_types.h:34:2: error: architecture not supported
#error architecture not supported
^
In file included from supported
/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/context_lite.cpp:1#error architecture not supported:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/context_lite.h ^:
17:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h:18:
In file included from /usr/include/c++/4.2.1/memory:53:
In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h:65:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:71:
In file included from /usr/include/_types.h:27:
In file included from /usr/include/sys/_types.h:32:
/usr/include/sys/cdefs.h:763:2: error: Unsupported architecture
#error Unsupported architecture
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/context_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/context_lite.h:17:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h:18:
In file included from /usr/include/c++/4.2.1/memory:53:
In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h:65:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:71:
In file included from /usr/include/_types.h:27:
In file included from /usr/include/sys/_types.h:33:
/usr/include/machine/_types.h:34:2: error: architecture not supported
#error architecture not supported
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/buffer_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/buffer_lite.h:18:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h:18:
In file included from /usr/include/c++/4.2.1/memory:53:
In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h:65:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:71:
In file included from /usr/include/_types.h:27:
In file included from /usr/include/sys/_types.h:32:
/usr/include/sys/cdefs.h:763:2: error: Unsupported architecture
#error Unsupported architecture
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/buffer_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/buffer_lite.h:18:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h:18:
In file included from /usr/include/c++/4.2.1/memory:53:
In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h:65:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:71:
In file included from /usr/include/_types.h:27:
In file included from /usr/include/sys/_types.h:33:
/usr/include/machine/_types.h:34:2: error: architecture not supported
#error architecture not supported
^
In file included from In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/buffer_lite.cpp/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.cpp::11:
:
In file included from In file included from In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/buffer_lite.h/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.h/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_lite.cpp:::18181:
:
:
In file included from In file included from In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/tensor_lite.h/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/teIn file included from nsor_lite.h/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/context_lite.cpp:::11918:
:
:
In file included from In file included from In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/context_lite.h/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/shape_lite.h/usr/include/c++/4.2.1/memory:::171753:
:
:
In file included from In file included from In file included from /usr/include/c++/4.2.1/vector/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h/usr/include/c++/4.2.1/bits/stl_algobase.h:::651865:
:
:
In file included from In file included from In file included from /usr/include/c++/4.2.1/bits/functexcept.h/usr/include/c++/4.2.1/memory/usr/include/c++/4.2.1/bits/c++config.h:::534141:
:
:
In file included from In file included from In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h/usr/include/c++/4.2.1/bits/c++config.h/usr/include/c++/4.2.1/bits/os_defines.h:::654161:
:
:
In file included from In file included from In file included from /usr/include/c++/4.2.1/bits/os_defines.h/usr/include/c++/4.2.1/bits/c++config.h/usr/include/unistd.h:::416171:
:
:
In file included from In file included from In file included from /usr/include/c++/4.2.1/bits/os_defines.h/usr/include/unistd.h/usr/include/_types.h:::617127:
:
:
In file included from In file included from /usr/include/unistd.h/usr/include/_types.h/usr/include/sys/_types.h:::277155:
:
:In file included from 9/usr/include/sys/_types.h/usr/include/_types.h::: 5527::
9error:/usr/include/sys/_types.h: :55:unknown9error :: type nameunknown error '__int64_t': type
name unknown'__int64_t' type
name '__int64_t'
typedef __int64_t __darwin_blkcnt_t; /* total blocks /
^
typedef __int64_t __darwin_blkcnt_t; / total blocks /
^typedef __int64_t __darwin_blkcnt_t; / total blocks */
^
:19:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/shape_lite.h:17:
In file included from /usr/include/c++/4.2.1/vector:65:
In file included from /usr/include/c++/4.2.1/bits/functexcept.h:41:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:71:
In file included from /usr/include/_types.h:27:
/usr/include/sys/_types.h:55:9: error: unknown type name '__int64_t'
typedef __int64_t __darwin_blkcnt_t; /* total blocks /
^
/usr/include/sys/_types.h:56/usr/include/sys/_types.h::956:: 9: error: error: unknown typeunknown nametype '__int32_t'name
'__int32_t'
typedef __int32_t __darwin_blksize_t; / preferred block size /typedef __int32_t __darwin_blksize_t; / preferred block size */
^ ^
/usr/include/sys/_types.h:56:9: error: unknown type name '__int32_t'
typedef __int32_t __darwin_blksize_t; /* preferred block size */
^
/usr/include/sys/_types.h:/usr/include/sys/_types.h57::579::9 : error: error: unknown unknowntype typename name'__int32_t' '__int32_t'
typedef __int32_t __darwin_dev_t; /* dev_t /
typedef __int32_t __darwin_dev_t; / dev_t /
^
^
/usr/include/sys/_types.h:57:9: error: unknown type name '__int32_t'
typedef __int32_t __darwin_dev_t; / dev_t /
^
/usr/include/sys/_types.h:60:9: error/usr/include/sys/_types.h:60:9: error: unknown type name '__uint32_t'
/usr/include/sys/_types.h:56:9: error: unknown /usr/include/sys/_types.htype: : 60:typedef __uint32_t __darwin_gid_t; / [???] process and gro...9unknown:
type ^errorname
: '__uint32_t'unknown
type name '__uint32_t'
typedef __uint32_t __darwin_gid_t; /* [???] process and gro...
typedef __uint32_t __darwin_gid_t; /* [???] process and gro...
^
^
/usr/include/sys/_types.h:61:9: error: unknown type name '__uint32_t'
/usr/include/sys/_types.h:61:9: error: unknowntypedef __uint32_t __darwin_id_t; /* [XSI] pid_t, uid_t, o...
type ^namename '__int32_t'
'__uint32_t'
typedef __int32_t __darwin_blksize_t; /* preferred block size /typedef __uint32_t __darwin_id_t; / [XSI] pid_t, uid_t, o...
^ ^
/usr/include/sys/_types.h:62:9: error: unknown type name '__uint64_t'
/usr/include/sys/_types.h:62:9: error: unknown type name '__uint64_t'/usr/include/sys/_types.h
:57:typedef __uint64_t __darwin_ino64_t; /* [???] Used for 64 bi...9
: ^
error: unknown type name '__int32_t'
typedef __uint64_t __darwin_ino64_t; /* [???] Used for 64 bi...
^
typedef __int32_t __darwin_dev_t; /* dev_t /
^
/usr/include/sys/_types.h:60:9: error: unknown type name '__uint32_t'
typedef __uint32_t __darwin_gid_t; / [???] process and gro...
^
/usr/include/sys/_types.h:61:9: error: unknown type/usr/include/sys/_types.h :name61 :'__uint32_t'9:
error: unknown type name '__uint32_t'
typedef __uint32_t __darwin_id_t; /* [XSI] pid_t, uid_t, o...
^
typedef __uint32_t __darwin_id_t; /* [XSI] pid_t, uid_t, o...
^
/usr/include/sys/_types.h:62:9: error: unknown/usr/include/sys/_types.h :type62 :name9 :'__uint64_t'
error: unknown type name '__uint64_t'
typedef __uint64_t __darwin_ino64_t; /* [???] Used for 64 bi...
^
typedef __uint64_t __darwin_ino64_t; /* [???] Used for 64 bi...
^
/usr/include/sys/_types.h:68:9: error: unknown type name '__darwin_natural_t'
typedef __darwin_natural_t __darwin_mach_port_name_t; /* Used by mach /
^
/usr/include/sys/_types.h:68:9: error: unknown type name '__darwin_natural_t'
typedef __darwin_natural_t __darwin_mach_port_name_t; / Used by mach /
^
/usr/include/sys/_types.h:70:9: error: unknown type name '__uint16_t'
typedef __uint16_t __darwin_mode_t; / [???] Some file attributes /
^
/usr/include/sys/_types.h:70:9: error: unknown type name '__uint16_t'
typedef __uint16_t __darwin_mode_t; / [???] Some file attributes /
^
/usr/include/sys/_types.h:71:9: error: unknown type name '__int64_t'
typedef __int64_t __darwin_off_t; / [???] Used for file sizes /
^
/usr/include/sys/_types.h:68:9: error: unknown type name '__darwin_natural_t'
typedef __darwin_natural_t __darwin_mach_port_name_t; / Used by mach /
^
/usr/include/sys/_types.h:71:9: error: unknown type name '__int64_t'
/usr/include/sys/_types.h:72:9typedef __int64_t __darwin_off_t; / [???] Used for file sizes /:
^error
: unknown type name '__int32_t'
typedef __int32_t __darwin_pid_t; / [???] process and gro...
^
/usr/include/sys/_types.h:70:9: error: unknown type name '__uint16_t'
/usr/include/sys/_types.h:72:typedef __uint16_t __darwin_mode_t; /* [???] Some file attributes /9
: ^
error: unknown type name '__int32_t'
/usr/include/sys/_types.h:73:9typedef __int32_t __darwin_pid_t; / [???] process and gro...:
^
error: unknown type name '__uint32_t'
typedef __uint32_t __darwin_sigset_t; /* [???] signal set /
^
/usr/include/sys/_types.h:71:9: error: unknown type name '__int64_t'
typedef __int64_t __darwin_off_t; / [???] Used for file sizes /
^
/usr/include/sys/_types.h:73:9: error/usr/include/sys/_types.h: :74:9:unknown type errorname: '__uint32_t'unknown
type name '__int32_t'
typedef __uint32_t __darwin_sigset_t; / [???] signal set /
^
typedef __int32_t __darwin_suseconds_t; / [???] microseconds /
^
/usr/include/sys/_types.h:68:9: /usr/include/sys/_types.h:72error:: 9: unknown type errorname: unknown '__darwin_natural_t'type
name '__int32_t'
typedef __darwin_natural_t __darwin_mach_port_name_t; / Used by mach /
^
typedef __int32_t __darwin_pid_t; / [???] process and gro...
^
/usr/include/sys/_types.h:74:9: error: unknown type name '__int32_t'
typedef __int32_t __darwin_suseconds_t; /* [???] microseconds /
^
/usr/include/sys/_types.h:73:9: /usr/include/sys/_types.herror:: 70:9unknown: type nameerror : '__uint32_t'
unknown type name '__uint16_t'
typedef __uint32_t __darwin_sigset_t; / [???] signal set /
^
typedef __uint16_t __darwin_mode_t; / [???] Some file attributes /
^
/usr/include/sys/_types.h:75:9: error: unknown type name '__uint32_t'
/usr/include/sys/_types.h:74:9: error: unknowntypedef __uint32_t __darwin_uid_t; / [???] user IDs /
type /usr/include/sys/_types.h ^name:
71'__int32_t':9
: error: unknown type name '__int64_t'
typedef __int32_t __darwin_suseconds_t; / [???] microseconds /
^
typedef __int64_t __darwin_off_t; / [???] Used for file sizes /
^
/usr/include/sys/_types.h:76:9: error: /usr/include/sys/_types.hunknown:75:9: /usr/include/sys/_types.h:72error:: 9: unknown typeerror : name '__uint32_t'unknown
type name '__int32_t'
typedef __uint32_t __darwin_uid_t; / [???] user IDs /
^
typedef __int32_t __darwin_pid_t; / [???] process and gro...
^
/usr/include/sys/_types.h:75:9: error: unknown type name '__uint32_t'
typedef __uint32_t __darwin_uid_t; /* [???] user IDs /
^
/usr/include/sys/_types.h:76:9: error: unknown type/usr/include/sys/_types.h :name73 :'__uint32_t'9:
error: unknown type name '__uint32_t'
typedef __uint32_t __darwin_useconds_t; / [???] microseconds /
^
typedef __uint32_t __darwin_sigset_t; / [???] signal set /
^
/usr/include/sys/_types.h:76:9: error: unknown type name '__uint32_t'
/usr/include/sys/_types.h:74:9: error: unknown type nametypedef __uint32_t __darwin_useconds_t; / [???] microseconds */
'__int32_t' ^
typedef __int32_t __darwin_suseconds_t; /* [???] microseconds /
^
/usr/include/sys/_types.h:75:9: errortype: unknown type name '__uint32_t'
typedef __uint32_t __darwin_uid_t; / [???] user IDs /
^
name '__uint32_t'
typedef __uint32_t __darwin_useconds_t; / [???] microseconds /
^
/usr/include/sys/_types.h:76:9: error: unknown type name '__uint32_t'
typedef __uint32_t __darwin_useconds_t; / [???] microseconds /
^
In file included from In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/context_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/context_lite.h:17:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h:18:
In file included from /usr/include/c++/4.2.1/memory:53:
In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h:65:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:180:
/usr/include/sys/_types/_size_t.h:31:9: error: unknown type name
'__darwin_size_t'; did you mean '__darwin_ino_t'?
typedef __darwin_size_t size_t;
^
/usr/include/sys/_types.h:64:26: note: '__darwin_ino_t' declared here
typedef __darwin_ino64_t __darwin_ino_t; / [???] Used for inodes /
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/tensor_lite.h:19:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/shape_lite.h:17:
In file included from /usr/include/c++/4.2.1/vector:65:
In file included from /usr/include/c++/4.2.1/bits/functexcept.h:41:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:180:
/usr/include/sys/_types/_size_t.h:31:9: error: unknown/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/buffer_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/buffer_lite.h:18:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h:18:
In file included from /usr/include/c++/4.2.1/memory:53:
In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h:65:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:180:
/usr/include/sys/_types/_size_t.h:31:9: error: unknown type name
'__darwin_size_t'; did you mean '__darwin_ino_t'?
typedef __darwin_size_t size_t;
^
/usr/include/sys/_types.h:64:26: note: '__darwin_ino_t' declared here
typedef __darwin_ino64_t __darwin_ino_t; / [???] Used for inodes /
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.h:18:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/tensor_lite.htype name
'__darwin_size_t'; did you mean '__darwin_ino_t'?
typedef __darwin_size_t size_t;
^
/usr/include/sys/_types.h:64:26: note: '__darwin_ino_t' declared here
:19:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/shape_lite.h:17:
In file included from /usr/include/c++/4.2.1/vectortypedef __darwin_ino64_t __darwin_ino_t; / [???] Used for inodes /:
65:
In file included from ^/usr/include/c++/4.2.1/bits/functexcept.h
:41:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:180:
/usr/include/sys/_types/_size_t.h:31:9: error: unknown type name
'__darwin_size_t'; did you mean '__darwin_ino_t'?
typedef __darwin_size_t size_t;
^
/usr/include/sys/_types.h:64:26: note: '__darwin_ino_t' declared here
typedef __darwin_ino64_t __darwin_ino_t; / [???] Used for inodes */
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/buffer_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/buffer_lite.h:18:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h:18:
In file included from /usr/include/c++/4.2.1/memory:53:
In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h:65:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:199:
In file included from /usr/include/sys/_types/_ssize_t.h:30:
/usr/include/machine/types.h:37:2: error: architecture not supported
#error architecture not supported
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/tensor_lite.h:19:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/shape_lite.h:17:
In file included from /usr/include/c++/4.2.1/vector:65:
In file included from /usr/include/c++/4.2.1/bits/functexcept.h:41:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:199:
In file included from /usr/include/sys/_types/_ssize_t.h:30:
/usr/include/machine/types.h:37:2: error: architecture not supported
#error architecture not supported
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/context_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/context_lite.h:17:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h:18:
In file included from /usr/include/c++/4.2.1/memory:53:
In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h:65:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:199:
In file included from /usr/include/sys/_types/_ssize_t.h:30:
/usr/include/machine/types.h:37:2: error: architecture not supported
#error architecture not supported
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/buffer_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/buffer_lite.h:18:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h:18:
In file included from /usr/include/c++/4.2.1/memory:53:
In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h:65:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:199:
/usr/include/sys/_types/_ssize_t.h:31:9: error: unknown type name
'__darwin_ssize_t'
typedef __darwin_ssize_t ssize_t;
^
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.h:18:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/tensor_lite.h:19:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/shape_lite.h:17:
In file included from /usr/include/c++/4.2.1/vector:65:
In file included from /usr/include/c++/4.2.1/bits/functexcept.h:41:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:199:
In file included from /usr/include/sys/_types/_ssize_t.h:30:
/usr/include/machine/types.h:37:2: error: architecture not supported
#error architecture not supported
^
fatal error: too many errors emitted, stopping now [-ferror-limit=]
In file included from In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/context_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/context_lite.h:17:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/common_lite.h:18:
In file included from /usr/include/c++/4.2.1/memory:53:
In file included from /usr/include/c++/4.2.1/bits/stl_algobase.h:65:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:199:
/usr/include/sys/_types/_ssize_t.h:31:9: error: unknown type name
'__darwin_ssize_t'
typedef __darwin_ssize_t ssize_t;
^
/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_lite.cpp:In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.cpp:1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.h:18:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/tensor_lite.h:19:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/shape_lite.h:17:
In file included from /usr/include/c++/4.2.1/vector:65:
In file included from /usr/include/c++/4.2.1/bits/functexcept.h:41:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:199:
/usr/include/sys/_types/_ssize_t.h:31:9: error: unknown type name
'__darwin_ssize_t'
typedef __darwin_ssize_t ssize_t;
^
1:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/tensor_lite.h:19:
In file included from /Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/tools/anakin-lite/../../saber/lite/../../saber/lite/core/shape_lite.h:17:
In file included from /usr/include/c++/4.2.1/vector:65:
In file included from /usr/include/c++/4.2.1/bits/functexcept.h:41:
In file included from /usr/include/c++/4.2.1/bits/c++config.h:41:
In file included from /usr/include/c++/4.2.1/bits/os_defines.h:61:
In file included from /usr/include/unistd.h:72:
In file included from /usr/include/sys/unistd.h:199:
/usr/include/sys/_types/_ssize_t.h:31:9: error: unknown type name
'__darwin_ssize_t'
typedef __darwin_ssize_t ssize_t;
^
fatal error: too many errors emitted, stopping now [-ferror-limit=]
fatal error: too many errors emitted, stopping now [-ferror-limit=]
fatal error: too many errors emitted, stopping now [-ferror-limit=]
20 errors generated.
make[2]: *** [CMakeFiles/ANAKIN_LITE_OBJS.dir/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/buffer_lite.cpp.o] Error 1
make[2]: *** Waiting for unfinished jobs....
20 errors generated.
20 errors generated.
make[2]: *** [CMakeFiles/ANAKIN_LITE_OBJS.dir/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_op_lite.cpp.o] Error 1
20 errors generated.
make[2]: *** [CMakeFiles/ANAKIN_LITE_OBJS.dir/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/tensor_lite.cpp.o] Error 1
make[2]: *** [CMakeFiles/ANAKIN_LITE_OBJS.dir/Users/v_zhangxiaoqing01/Desktop/新/Anakin-arm_lite/saber/lite/core/context_lite.cpp.o] Error 1
make[1]: *** [CMakeFiles/ANAKIN_LITE_OBJS.dir/all] Error 2
make: *** [all] Error 2
使用ubuntu 16.04 编译报错，gcc版本5.4。报错信息如下：
/usr/include/c++/5/bits/stl_function.h:357:20: error: no match for ‘operator==’ (operand types are ‘const anakin::graph::io’ and ‘const anakin::graph::io’) { return __x == __y; }
Thanks, I can only find the android build tutorial in your doc.
config.yaml
OPTIONS:
Framework: CAFFE
SavePath: ./output
ResultName: ocr
Config:
LaunchBoard: ON
Server:
ip: 0.0.0.0
port: 8888
OptimizedGraph:
enable: OFF
path: ./anakin_optimized/ocr.anakin.bin.saved
LOGGER:
LogToPath: ./log/
WithColor: ON
TARGET:
CAFFE:
# path to proto files
ProtoPaths:
- /home/kezunlin/program/caffe/src/caffe/proto/caffe.proto
PrototxtPath: ./input_model/ocr/ocr.prototxt
ModelPath: ./input_model/mnist/ocr.caffemodel
run converter and get error output:
$ python converter.py
INF | 2018-09-20 14:02:34.567382 | __init__.py:20 <module>() ] Import Module: caffe_pb2
INF | 2018-09-20 14:02:34.581084 | parser_caffe.py:470 _Parsing_new() ] [CAFFE] Parsing ...
Traceback (most recent call last):
File "converter.py", line 20, in <module>
graph = Graph(config)
File "/home/kezunlin/program/anakin/tools/external_converter_v2/parser/graph.py", line 39, in __init__
self.graph_io = self.parser()
File "/home/kezunlin/program/anakin/tools/external_converter_v2/parser/caffe/parser_caffe.py", line 34, in __call__
return self._Parsing_new()
File "/home/kezunlin/program/anakin/tools/external_converter_v2/parser/caffe/parser_caffe.py", line 471, in _Parsing_new
self._DetectionArch()
File "/home/kezunlin/program/anakin/tools/external_converter_v2/parser/caffe/parser_caffe.py", line 41, in _DetectionArch
self._FilterNet()
File "/home/kezunlin/program/anakin/tools/external_converter_v2/parser/caffe/parser_caffe.py", line 389, in _FilterNet
assert layer.name not in filtered_layer_names, " layer_name : %s" % (layer.name)
AssertionError: layer_name : fusion5
I would like to point out that an identifier like "_Op" does eventually not fit to the expected naming convention of the C++ language standard.
Would you like to adjust your selection for unique names?
Before we make the project, it will check the dependences in cmake cmd. After cmake, we make the project. However, it still download some third party libraries from Internet. The downloading behavior should not in makefile.
Hello, I want to benchmark Anakin in ios device. But, I can't find relate informataion in Anakin's wiki page. Do you have verified Anakin in ios devices？ Thanks.
WAN| 08:46:02.00618| 6.902s| main_thread| parser.cpp:138] Parsing in edges of node : relu5_4
FTL| 08:46:02.00618| 6.902s| main_thread| graph_base.inl:57] Check failed: (this->has_vertex(arc.bottom()) && this->has_vertex(arc.top())) The arc's top or bottom is not vertex!
*** Check failed: (this->has_vertex(arc.bottom()) && this->has_vertex(arc.top())) fatal error: stack trace: ***
6 0x4a3329 ./anakin_demo() [0x4a3329]
5 0x7febe6ff2830 __libc_start_main + 240 [??:0]
4 0x4a420b ./anakin_demo() [0x4a420b]
3 0x7febe8878e96 anakin::graph::Graph<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, (anakin::Precision)0>::load(std::string) + 202 [??:0]
2 0x7febe877e99a anakin::Status anakin::parser::load<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, (anakin::Precision)0>(anakin::graph::Graph<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, (anakin::Precision)0>, std::string&) + 69 [??:0]
1 0x7febe877f4d2 anakin::Status anakin::parser::load<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, (anakin::Precision)0>(anakin::graph::Graph<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, (anakin::Precision)0>, char const*) + 2656 [??:0]
0 0x4e5cbd anakin::graph::GraphBase<std::string, std::shared_ptr<anakin::graph::Node<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, (anakin::Precision)0> >, anakin::saber::Tensor<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, anakin::saber::NCHW>*, anakin::graph::Edge<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1> >::add_in_arc(anakin::graph::Edge<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1>&) + 451 [??:?]
when I complied with release flag, benchmark will exit with segment fault, but debug will be ok
@Superjomn Hi, I just want to compare the performance of anakin_sass with the performance of [email protected] for convolution operator, and I have successfully compared on fp32 data-format.
However, when I tried fp16 data-format, I encountered that error of undefined reference to `void anakin::saber::direct_conv_bias_Kdivis4<__half, __half>, does libanakin_saber_sass_sm_61.a support fp16 data-format?
make会提示如下错误，直接解开tar包是没问题的，mklml的包也成功下载下来了，多次编译也不能通过
[ 1%] Performing download step for 'extern_mklml'
--2018-05-30 21:14:26-- http://paddlepaddledeps.cdn.bcebos.com/mklml_lnx_2018.0.3.20180406.tgz
正在解析主机 paddlepaddledeps.cdn.bcebos.com (paddlepaddledeps.cdn.bcebos.com)... 221.195.34.35
正在连接 paddlepaddledeps.cdn.bcebos.com (paddlepaddledeps.cdn.bcebos.com)|221.195.34.35|:80... 已连接。
已发出 HTTP 请求，正在等待回应... 416 Requested Range Not Satisfiable
文件已下载完成；不会进行任何操作。
tar: DOWNLOAD_NO_PROGRESS：归档中找不到
tar: 1：归档中找不到
tar: 由于前次错误，将以上次的错误状态退出
make[2]: *** [third-party/mklml/src/extern_mklml-stamp/extern_mklml-download] 错误 2
make[1]: *** [CMakeFiles/extern_mklml.dir/all] 错误 2
make: *** [all] 错误 2
Hello, I run Anakin arm branch for benchmark squeezenet_v1.1 and vgg16, but I get a wrong result. Net output is all Zero. I have verify my code in mobilenet 1.0, I can get the right result. But, with squeezenet_v1.1 and vgg16, some wrong happen.
I don`t get warning when load net parameter, that mean all operators should been support by Anakin. Log also show "constructs the executer net success".
I want to know what happen? Do you have verify you code in squeezenet and vgg16?
Thanks !!!
request.h:30:63: error: cannot call member function ‘const string anakin::type_id::type_info() [with T = void; std::__cxx11::string = std::__cxx11::basic_string]’ without object
const std::string info = anakin::type_id::type_info();
Anakin/framework/core/operator/operator.h:120:67: error: expected primary-expression before ‘>’ token
T get_attr(std::string attr_name) { return _node_p->get_attr(attr_name); }
base.h has some wrong impl init.
code here：
auto status = graph->load("./output/lenet.anakin.bin");
graph->ResetBatchSize("input_0", batch_size);
graph->Reshape("input_0", {1, 1, 28, 28});
//! optimize the graph
LOG(INFO) << "optimize the graph";
graph->Optimize();
it's crash when run at "graph->Optimize()".
error here:
if I comment graph->Optimize() ,there will be all dim of input is 0.
auto d_tensor_in_p = net_executer.get_in("input_0");
auto valid_shape_in = d_tensor_in_p->valid_shape();
for (int i = 0; i < valid_shape_in.size(); i++) {
LOG(INFO) << "detect input dims[" << i << "]" << valid_shape_in[i];
}
Dockerfile can't be built successfully
Hi!, I am interested in the Anakin project.
I would like to know if there are any supports & benchmark results for int8? If not, will there be any? thx!
I am curious about how you implement depthwise plugin layer in TRT by yourselves? The MobileNet v1, v2 test results do not make sense to me. Why so little latency difference between batchsize=1 and 2?
tensores are not synced when ops are launched in different streams
I followed the anakin docker guide guide.
and issue the command
sudo ./anakin_docker_build_and_run.sh -p NVIDIA-GPU -o Ubuntu -m Build
error occur:
-- cudnn include header is CUDNN_INCLUDE_DIR-NOTFOUND/cudnn.h
-- cudnn library is /usr/lib/x86_64-linux-gnu/libcudnn.so/libcudnn.so
CMake Error at cmake/cuda.cmake:126 (message):
Could not find cudnn library in:
Call Stack (most recent call first):
cmake/gather.cmake:16 (anakin_find_cudnn)
CMakeLists.txt:178 (include)
-- Found CUDA: /usr/local/cuda (found suitable version "8.0", minimum required is "7.5")
-- Building fat-bin for cuda code !
-- `--support arch : 3.5
-- `--support arch : 5.0
-- `--support arch : 6.0
-- `--support arch : 6.1
-- Looking for include file pthread.h
-- Looking for include file pthread.h - found
-- Looking for pthread_create
-- Looking for pthread_create - not found
-- Looking for pthread_create in pthreads
-- Looking for pthread_create in pthreads - not found
-- Looking for pthread_create in pthread
-- Looking for pthread_create in pthread - found
-- Found Threads: TRUE
-- Found PROTOBUF: /usr/local/lib/libprotobuf.so
-- Found protobuf in /usr/local/include
--
-- ================================ configuration ==================================
-- General:
-- anakin version : 0.1.2
-- System : Linux
-- C++ compiler : /usr/bin/c++
-- C flags :
-- CXX flags : -std=c++11 -fPIC -ldl -lrt -W -pthread -Wno-unused-variable -fpermissive -fdiagnostics-show-option -Wno-undef -Wno-narrowing -Wno-unknown-pragmas -Wno-delete-non-virtual-dtor -Wno-comment -Wno-sign-compare -Wno-ignored-qualifiers -Wno-enum-compare -O3 -DNDEBUG
-- Build type : Release;FORCE
-- Build cross plantform : ON
-- Build anakin fp32 : ON
--
-- Build shared libs : YES
-- Build with unit test : YES
--
-- Enable verbose message : NO
-- Enable noisy warnings : NO
-- Disable all warnings : YES
--
-- Use local logger : logger
-- Use google protobuf : ON
-- Use local Unit test : aktest
-- USE_OPENCV : OFF
-- USE_BOOST : OFF
-- USE_OPENMP :
--
-- Cuda:
-- USE_CUDA : ON
-- |--CUDA version : 8.0
-- `--NVCC flags : -Xcompiler -fPIC -O3 -std=c++11 --default-stream per-thread -Wno-deprecated-gpu-targets --generate-code arch=compute_35,code=sm_35 --generate-code arch=compute_50,code=sm_50 --generate-code arch=compute_60,code=sm_60 --generate-code arch=compute_61,code=sm_61
-- USE_CUBLAS : ON
-- USE_CURAND : ON
-- USE_CUFFT : ON
-- USE_CUDNN : ON
-- `--Cudnn version :
--
-- USE_OPENCL : OFF
--
-- SELECT_GPU_PLACE : YES
--
-- Configuation path : /Anakin/gpu_build_sm61/anakin_config.h
-- ================================ End ==================================
-- Configuring incomplete, errors occurred!
See also "/Anakin/gpu_build_sm61/CMakeFiles/CMakeOutput.log".
See also "/Anakin/gpu_build_sm61/CMakeFiles/CMakeError.log".
make: *** No targets specified and no makefile found. Stop.
sha256:694bca37cbee627f47bfc46e71af099147bb61045fddf6ec3abd1beeab69d00d
Hi, I have a new question,
Does Anakin support “variadic” input shapes? For example, in frame 1, I have one standard 224224 image as input. But in frame 2, I have another image of any arbitrary size like 456789. I would like to know if Anakin could support.
Thank you~ ~
config.yaml的文件内容如下:
OPTIONS:
Framework: CAFFE
SavePath: ./output
ResultName: mobilenet-ssd
Config:
LaunchBoard: ON
Server:
ip: 0.0.0.0
port: 8888
OptimizedGraph:
enable: OFF
path: /home/public/CLionProjects/Anakin/tools/external_converter_v2/anakin_optimized/mobilenet.anakin.bin.saved
LOGGER:
LogToPath: ./log/
WithColor: ON
TARGET:
CAFFE:
# path to proto files
ProtoPaths:
- /home/public/CLionProjects/Anakin/tools/external_converter_v2/caffe.proto
PrototxtPath: /home/public/CLionProjects/Anakin/tools/external_converter_v2/mobilenet-ssd/MobileNetSSD_deploy.prototxt
ModelPath: /home/public/CLionProjects/Anakin/tools/external_converter_v2/mobilenet-ssd/MobileNetSSD_deploy.caffemodel
其中caffe.proto文件使用来源为:https://github.com/weiliu89/caffe/blob/ssd/src/caffe/proto/caffe.proto
MobileNet-SSD模型来源为:https://github.com/chuanqi305/MobileNet-SSD
运行python converter.py命令,执行过程中出现如下错误:
INF | 2018-09-12 19:56:12.527134 | parser_caffe.py:539 _Parsing_new() ] `--[ Match ]Parsing [Permute: conv11_mbox_conf_perm]
INF | 2018-09-12 19:56:12.527407 | parser_caffe.py:524 _Parsing_new() ] Dectect [Flatten: conv11_mbox_conf_flat]
INF | 2018-09-12 19:56:12.527663 | parser_caffe.py:539 _Parsing_new() ] `--[ Match ]Parsing [Flatten: conv11_mbox_conf_flat]
INF | 2018-09-12 19:56:12.527922 | parser_caffe.py:524 _Parsing_new() ] Dectect [PriorBox: conv11_mbox_priorbox]
INF | 2018-09-12 19:56:12.528170 | parser_caffe.py:539 _Parsing_new() ] `--[ Match ]Parsing [PriorBox: conv11_mbox_priorbox]
Traceback (most recent call last):
File "converter.py", line 20, in <module>
graph = Graph(config)
File "/home/public/CLionProjects/Anakin/tools/external_converter_v2/parser/graph.py", line 39, in __init__
self.graph_io = self.parser()
File "/home/public/CLionProjects/Anakin/tools/external_converter_v2/parser/caffe/parser_caffe.py", line 34, in __call__
return self._Parsing_new()
File "/home/public/CLionProjects/Anakin/tools/external_converter_v2/parser/caffe/parser_caffe.py", line 570, in _Parsing_new
CAFFE_LAYER_PARSER[source_layer_type](nodeIO, rlayer, tensors, opIO) # call parser automatically
File "/home/public/CLionProjects/Anakin/tools/external_converter_v2/parser/operations/op.py", line 42, in __call__
return self.parser(args)
File "/home/public/CLionProjects/Anakin/tools/external_converter_v2/parser/caffe/caffe_layer_param_transmit.py", line 39, in warpper_args
Parser(args)
File "/home/public/CLionProjects/Anakin/tools/external_converter_v2/parser/caffe/caffe_layer_param_transmit.py", line 1081, in Parser_priorbox
OpsRegister()["PriorBox"].fixed_size = list(prior_box_param.fixed_size)
AttributeError: 'PriorBoxParameter' object has no attribute 'fixed_size'
请求帮助,非常感谢!
请问有没有例子演示 改变输入的尺寸？
第一次输入{1，3，800，600}
第二次输入{1，3，400，400}
这样改变宽高的
或者
宽高不变改变batchsize？
请问 developing 分支和 dev_2 有什么区别？,我发现更新 dev_2 比 developing 要快
liuhao@umaster:~/OpenSource/Anakin/tools/external_converter_v2$ python converter.py
Traceback (most recent call last):
File "converter.py", line 16, in
from parser import *
File "/home/liuhao/OpenSource/Anakin/tools/external_converter_v2/parser/init.py", line 8, in
from graph import *
File "/home/liuhao/OpenSource/Anakin/tools/external_converter_v2/parser/graph.py", line 6, in
from proto import *
File "/home/liuhao/OpenSource/Anakin/tools/external_converter_v2/parser/proto/init.py", line 5, in
from graph_pb2 import *
File "/home/liuhao/OpenSource/Anakin/tools/external_converter_v2/parser/proto/graph_pb2.py", line 15, in
import node_pb2 as node__pb2
File "/home/liuhao/OpenSource/Anakin/tools/external_converter_v2/parser/proto/node_pb2.py", line 15, in
import operator_pb2 as operator__pb2
File "/home/liuhao/OpenSource/Anakin/tools/external_converter_v2/parser/proto/operator_pb2.py", line 22, in
serialized_pb=_b('\n\x0eoperator.proto"e\n\x07OpProto\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\x16\n\x0eis_commutative\x18\x02 \x01(\x08\x12\x0e\n\x06in_num\x18\x03 \x01(\x05\x12\x0f\n\x07out_num\x18\x04 \x01(\x05\x12\x13\n\x0b\x64\x65scription\x18\x05 \x01(\tb\x06proto3')
TypeError: new() got an unexpected keyword argument 'serialized_options'
Function: pooling3x3s2_max ( arm/impl/pooling_arm_impl.cpp )
Layer Definition:
layer {
name: "Pooling1"
type: "Pooling"
bottom: "Convolution3"
top: "Pooling1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
Input dim: 1, 64, 61, 61
Output dim: 1, 64, 30, 30
Input Values:
<0, 0>:0.072792
...
<1, 57>: 0.021526
<1, 58>: 0.021526
<1, 59>: 0.021526
<1, 60>: 0.041485
Output Values:
<0, 27>:0.021526
<0, 28>:0.021526
<0, 29>:0.021526
<1, 0>: 0.072792
I think Output<0, 29> must be 0.041485.
Please check and fix bug asap.
按照如下步骤进行anakin的安装：
https://github.com/PaddlePaddle/Anakin/blob/developing/docs/Manual/INSTALL_ch.md
环境：
ubuntu18.04
make --version GNU Make 4.1
g++ --version g++ (Ubuntu 7.3.0-16ubuntu3) 7.3.0
cmake --version cmake version 3.10.2
protoc --version libprotoc 3.6.1
执行下面命令时：
$ sh Anakin/tools/x86_build.sh
出现以下error：
/home/Anakin/saber/funcs/impl/x86/saber_gru.h:10:24: error: ‘__m256’ was not declared in this scope
#define SABER_X86_TYPE __m256
^
/home/Anakin/saber/funcs/impl/x86/saber_gru.h:58:38: note: in expansion of macro ‘SABER_X86_TYPE’
int aligned_byte= sizeof(SABER_X86_TYPE);
^~~~~~~~~~~~~~
/home/Anakin/saber/funcs/impl/x86/saber_gru.h:10:24: note: suggested alternative: ‘__modf’
#define SABER_X86_TYPE __m256
^
/home/Anakin/saber/funcs/impl/x86/saber_gru.h:58:38: note: in expansion of macro ‘SABER_X86_TYPE’
int aligned_byte= sizeof(SABER_X86_TYPE);
^~~~~~~~~~~~~~
saber/CMakeFiles/anakin_saber_common.dir/build.make:494: recipe for target 'saber/CMakeFiles/anakin_saber_common.dir/funcs/impl/x86/saber_gru.cpp.o' failed
make[2]: *** [saber/CMakeFiles/anakin_saber_common.dir/funcs/impl/x86/saber_gru.cpp.o] Error 1
make[2]: *** Waiting for unfinished jobs....
CMakeFiles/Makefile2:140: recipe for target 'saber/CMakeFiles/anakin_saber_common.dir/all' failed
make[1]: *** [saber/CMakeFiles/anakin_saber_common.dir/all] Error 2
Makefile:129: recipe for target 'all' failed
make: *** [all] Error 2
There is NOT a "Inlcude" folder in Anakin root folder or in the build folder, so it is really diffucult to find the head files.
In the examples, it includes some head files, but I can NOT find them in the root folder and build folder.
#include "utils/logger/logger.h"
#include "graph.h"
#include `"net.h"
how to set gpu id ?
Hi,
Will Windows be supported?
Thanks
I have converted the Mobilenet-SSD caffemodel to anakin model, it generated a file named mobilenet_ssd.anakin.bin. Then I use the example example_nv_cnn_net.cpp to test my bin file, but I got the error:
`0| 11:20:33.00349| 0.436s| 1F5B7040| cuda_device.cpp:45] Device id: 0 , name: Quadro K1200
0| 11:20:33.00349| 0.436s| 1F5B7040| cuda_device.cpp:47] Multiprocessors: 4
0| 11:20:33.00349| 0.436s| 1F5B7040| cuda_device.cpp:50] frequency:1032MHz
0| 11:20:33.00349| 0.436s| 1F5B7040| cuda_device.cpp:52] CUDA Capability : 5.0
0| 11:20:33.00349| 0.436s| 1F5B7040| cuda_device.cpp:54] total global memory: 4041MBytes.
0| 11:20:33.00350| 0.437s| 1F5B7040| cuda_device.cpp:45] Device id: 1 , name: Quadro K1200
0| 11:20:33.00350| 0.437s| 1F5B7040| cuda_device.cpp:47] Multiprocessors: 4
0| 11:20:33.00350| 0.437s| 1F5B7040| cuda_device.cpp:50] frequency:1032MHz
0| 11:20:33.00350| 0.437s| 1F5B7040| cuda_device.cpp:52] CUDA Capability : 5.0
0| 11:20:33.00350| 0.437s| 1F5B7040| cuda_device.cpp:54] total global memory: 4041MBytes.
WAN| 11:20:33.00529| 0.617s| 1F5B7040| net.cpp:665] Current used device id : 0
WAN| 11:20:33.00532| 0.619s| 1F5B7040| input.cpp:16] Parsing Input op parameter.
0| 11:20:33.00532| 0.619s| 1F5B7040| input.cpp:19] |-- shape [0]: 1
0| 11:20:33.00532| 0.619s| 1F5B7040| input.cpp:19] |-- shape [1]: 3
0| 11:20:33.00532| 0.619s| 1F5B7040| input.cpp:19] |-- shape [2]: 300
0| 11:20:33.00532| 0.619s| 1F5B7040| input.cpp:19] |-- shape [3]: 300
FTL| 11:20:33.00532| 0.619s| 1F5B7040| node.h:180] Target attr name(weight_2) not found.
*** fatal error stack trace: ***:
6 0x4115d9 ./a.out() [0x4115d9]
5 0x7ff054ca2b45 __libc_start_main + 245
4 0x411cdf ./a.out() [0x411cdf]
3 0x7ff055c633fc anakin::Net<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, (anakin::Precision)0, (anakin::OpRunType)1>::Net(anakin::graph::Graph<anakin::saber::TargetType<(anakin::saber::TargetTypeE
num)1>, (anakin::saber::DataType)1, (anakin::Precision)0>&, bool) + 172
2 0x7ff055c626ca anakin::Net<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>,(anakin::saber::DataType)1, (anakin::Precision)0,(anakin::OpRunType)1>::init(anakin::graph::Graph<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, (anakin::Precision)0>&) + 1034
1 0x7ff055dca3d0 anakin::ops::SassConvReluHelper<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, (anakin::Precision)0>::InitParam() + 752
0 0x7ff055c62296 anakin::PBlock<float, anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1> > anakin::graph::Node<anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1>, (anakin::saber::DataType)1, (anakin::Precision)0>::get_attr<anakin::PBlock<float, anakin::saber::TargetType<(anakin::saber::TargetTypeEnum)1> > >(std::string&) + 182
Aborted`
what is the wrong? I can't understand the error information.
Would you like to wrap any pointers with the class template “std::unique_ptr”?
Thanks for the great library.
I want to run mobilenet (in benchmark example) on ARM in jni and model was converted successfully.
I follow the arm inference example classification.cpp.
Model loaded successfully and graph.get_outs() returns OK.
But when call
Net<ARM, AK_FLOAT, Precision::FP32, OpRunType::SYNC> net_executer(graph, ctx1, true);
app crashes.
Crash context is following module in net.cpp.
template<typename Ttype, DataType Dtype, Precision Ptype, OpRunType RunType>
void Net<Ttype, Dtype, Ptype, RunType>::init(graph::Graph<Ttype, Dtype, Ptype>& graph,
OpContextPtr ctx) {
init_env(graph);
// shallow copy
_graph_p->CopyFrom(graph);
auto node_names_in_exec_order = graph.get_nodes_in_order();
// infer basic shape and parsing parameter from graph
for (auto& node_name : node_names_in_exec_order) {
auto node_ptr = (*_graph_p)[node_name];
//LOG(ERROR) << "get node " << node_name << ", op type " << node_ptr->get_op_name();
if (node_ptr->get_op_name() == "Output") {
continue;
}
// create operations
auto* op_pointer = OpFactory<Ttype, Dtype, Ptype>::Global()[node_ptr->get_op_name()]; // Crash
node_ptr->get_op_name() is "Input".
Global().get_list_op_name() returns empty list.
What can be the issue?
Hope to any suggestions.
Thanks for the great library.
I want to run my model on ARM and model was converted successfully.
I follow the arm inference example classification.cpp.
Model loaded successfully and graph.get_outs() returns OK.
But d_tensor_in_p->valid_shape() returns all 0.
I can see the correct shapes on web model dashboard.
Net<ARM, AK_FLOAT, Precision::FP32, OpRunType::SYNC> net_executer(graph, ctx1, true);
//! get in
LOG(INFO) << "get input";
auto d_tensor_in_p = net_executer.get_in("input_0");
auto valid_shape_in = d_tensor_in_p->valid_shape();
for (int i = 0; i < valid_shape_in.size(); i++) {
LOG(INFO) << "detect input dims[" << i << "]" << valid_shape_in[i];
}
I've used exactly same code from classification.cpp.
Hope to any suggestions.
seems it uses all gpus, is there a way to specify one?
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
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 ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.