paddlepaddle / anakin Goto Github PK

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

CMake 1.63% Shell 0.29% C++ 80.65% C 1.90% Cuda 4.95% Python 5.19% JavaScript 5.10% CSS 0.14% HTML 0.13% Dockerfile 0.03%

ai inference-engine arm nvidia amd intel bitmain cambricon high-performance cross-platform

anakin's Introduction

Anakin2.0

Welcome to the Anakin GitHub.

Anakin is a cross-platform, high-performance inference engine, which is originally developed by Baidu engineers and is a large-scale application of industrial products.

Please refer to our release announcement to track the latest feature of Anakin.

Features

Flexibility

Anakin is a cross-platform, high-performance inference engine, supports a wide range of neural network architectures and different hardware platforms. It is easy to run Anakin on GPU / x86 / ARM platform.

Anakin has integrated with NVIDIA TensorRT and open source this part of integrated API to provide services, developers can call the API directly or modify it as needed, which will be more flexible for development requirements.
High performance

In order to give full play to the performance of hardware, we optimized the forward prediction at different levels.
- Automatic graph fusion. The goal of all performance optimizations under a given algorithm is to make the ALU as busy as possible. Operator fusion can effectively reduce memory access and keep the ALU busy.
- Memory reuse. Forward prediction is a one-way calculation. We reuse the memory between the input and output of different operators, thus reducing the overall memory overhead.
- Assembly level optimization. Saber is a underlying DNN library for Anakin, which is deeply optimized at assembly level.

NV GPU Benchmark

Machine And Enviornment

CPU: Intel(R) Xeon(R) CPU 5117 @ 2.0GHz
GPU: Tesla P4
cuda: CUDA8
cuDNN: v7

Time：warmup 10，running 1000 times to get average time
Latency (ms) and Memory(MB) of different batch

The counterpart of Anakin is the acknowledged high performance inference engine NVIDIA TensorRT 5 , The models which TensorRT 5 doesn't support we use the custom plugins to support.

VGG16

Batch_Size	RT latency FP32(ms)	Anakin2 Latency FP32 (ms)	RT Memory (MB)	Anakin2 Memory (MB)
1	8.52532	8.2387	1090.89	702
2	14.1209	13.8772	1056.02	768.76
4	24.4529	24.3391	1002.17	840.54
8	46.7956	46.3309	1098.98	935.61

Resnet50

Batch_Size	RT latency FP32(ms)	Anakin2 Latency FP32 (ms)	RT Latency INT8 (ms)	Anakin2 Latency INT8 (ms)	RT Memory FP32(MB)	Anakin2 Memory FP32(MB)
1	4.6447	3.0863	1.78892	1.61537	1134.88	311.25
2	6.69187	5.13995	2.71136	2.70022	1108.86	382
4	11.1943	9.20513	4.16771	4.77145	885.96	406.86
8	19.8769	17.1976	6.2798	8.68197	813.84	532.61

Resnet101

Batch_Size	RT latency (ms)	Anakin2 Latency (ms)	RT Latency INT8 (ms)	Anakin2 Latency INT8 (ms)	RT Memory (MB)	Anakin2 Memory (MB)
1	9.98695	5.44947	2.81031	2.74399	1159.16	500.5
2	17.3489	8.85699	4.8641	4.69473	1158.73	492
4	20.6198	16.8214	7.11608	8.45324	1021.68	541.08
8	31.9653	33.5015	11.2403	15.4336	914.49	611.54

X86 CPU Benchmark

Machine And Enviornment

CPU: Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz with HT, for FP32 test
CPU: Intel(R) Xeon(R) Gold 6271 CPU @ 2.60GHz with HT, for INT8 test
System: CentOS 6.3 with GCC 4.8.2, for benchmark between Anakin and Intel Caffe

All test enable 8 thread parallel
Time：warmup 10，running 200 times to get average time

The counterpart of Anakin is Intel Cafe(1.1.6) with mklml.

Net_Name	Batch_Size	Anakin2 Latency(2650v4) fp32 (ms)	caffe Latency(2650v4) fp32 (ms)	Anakin2 Latency int8(6271) (ms)
resnet50	1	20.6201	24.1369	3.20866
resnet50	2	39.2286	43.1096	5.44311
resnet50	4	77.1392	81.8814	9.93424
resnet50	8	152.941	158.321	19.5618
vgg16	1	55.6132	70.532	15.3181
vgg16	2	96.5034	131.451	22.5082
vgg16	4	180.479	247.926	37.2974
vgg16	8	346.619	485.44	67.6682
mobilenetv1	1	3.98104	5.42775	0.926546
mobilenetv1	2	7.27079	9.16058	1.35007
mobilenetv1	4	14.4029	16.2505	2.37271
mobilenetv1	8	29.1651	29.8381	3.75992
vgg16_ssd	1	125.948	143.412
vgg16_ssd	2	247.242	266.22
vgg16_ssd	4	488.377	510.978
vgg16_ssd	8	972.762	995.407
mobilenetv2	1	3.78504	23.0066
mobilenetv2	2	7.24622	65.9301
mobilenetv2	4	13.7638	85.3893
mobilenetv2	8	28.4093	131.669

ARM CPU Benchmark

Machine And Enviornment

CPU: Kirin 980
CPU: Snapdragon 652
CPU: Snapdragon 855
CPU: RK3399

Compile circumstance: Android ndk cross compile，gcc 4.9，enable neon
Time：warmup 10，running 10 times to get average time
Note: 1、shufflenetv2 int8 model add swish operator

The counterpart of Anakin is ncnn(20190320). This benchmark we test ARMv7 ARMv8 splitly

ARMv8 TEST

ABI： arm64-v8a

Latency (ms) of one batch

Kirin 980	Anakin fp32			Anakin int8			NCNN fp32			NCNN int8
	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread
mobilenet_v1	34.172	19.369	12.723	37.588	20.692	13.280	45.420	24.220	16.730	50.560	27.820	20.010
mobilenet_v2	30.489	17.784	12.327	29.581	17.208	15.307	30.390	17.310	12.900
mobilenet_ssd	71.609	37.477	28.952				88.220	70.070	66.430	103.700	85.160	85.320
resnet50	255.748	137.842	104.628				1299.480	695.830	498.010	243.360	131.100	89.800
shufflenetv1	11.544	8.931	7.027				12.810	9.390	8.030
shufflenetv2	11.687	7.899	5.321	20.402	11.529	9.061
squeezenet	28.580	16.638	14.435
googlenet	93.917	52.742	40.301	130.875	72.522	54.204

Snapdragon 855	Anakin fp32			Anakin int8			NCNN fp32			NCNN int8
	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread
mobilenet_v1	32.019	19.024	10.491	34.363	20.292	10.382	37.110	22.310	13.520	47.430	28.350	15.830
mobilenet_v2	28.533	17.455	10.433	24.487	15.182	9.133	25.060	15.970	11.250
mobilenet_ssd	66.454	41.397	23.639				101.560	69.380	43.930	136.420	91.010	47.490
resnet50	201.362	132.133	78.300				1141.290	724.090	385.990	229.020	138.450	82.060
shufflenetv1	10.153	7.101	5.327				11.610	8.020	5.870
shufflenetv2	10.868	6.713	4.526	17.306	10.987	6.788
squeezenet	25.880	16.134	9.697
googlenet	85.774	54.518	34.025	118.120	73.686	41.865

Snapdragon 652	Anakin fp32			Anakin int8			NCNN fp32			NCNN int8
	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread
mobilenet_v1	109.994	54.937	33.174	83.887	43.639	24.665	123.320	122.670	65.100	128.800	154.370	125.570
mobilenet_v2	80.712	46.314	30.874	69.340	43.590	31.864	89.920	90.900	55.320
mobilenet_ssd	246.459	121.684	134.019				248.190	138.170	142.350	247.020	145.080	211.000
resnet50	673.285	346.287	378.065				880.940	514.190		533.760	313.630
shufflenetv1	34.948	26.635	21.571				39.950	25.520	20.180
shufflenetv2	35.530	21.440	16.434	49.498	29.116	19.346
squeezenet	87.037	47.192	28.663
googlenet	268.023	148.533	95.624	236.492	131.510	81.561

RK3399	Anakin fp32			Anakin int8			NCNN fp32			NCNN int8
	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread
mobilenet_v1	111.317	60.008		87.201	45.693		149.270	91.200		142.790	86.140
mobilenet_v2	105.767	60.899		79.065	53.914		118.530	86.900
mobilenet_ssd	232.923	128.337					268.900	157.860		256.560	149.730
resnet50	671.800	369.386					1029.300	571.230		569.250	344.830
shufflenetv1	38.761	25.971
shufflenetv2	36.220	22.095		51.879	30.351
squeezenet	98.489	54.863
googlenet	274.166	159.429		235.085	133.044

ARMv7 TEST

ABI： armveabi-v7a with neon

Latency (ms) of one batch

Kirin 980	Anakin fp32			Anakin int8			NCNN fp32			NCNN int8
	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread
mobilenet_v1	39.051	19.813	14.184	39.026	22.048	14.250	50.240	26.850	20.010	92.900	49.420	37.160
mobilenet_v2	36.052	19.550	14.507	32.656	19.641	15.735	35.890	20.730	18.550
mobilenet_ssd	83.474	44.530	33.116				99.960	53.160	84.360	180.000	91.380	68.140
resnet50	291.478	158.954	129.484				1412.37	766.62	560.760	355.010	189.18	133.410
shufflenetv1	11.909	9.761	7.441				16.030	10.660	8.120
shufflenetv2	11.755	7.983	6.289	21.968	14.111	9.888
squeezenet	30.148	20.908	17.084
googlenet	108.210	65.798	58.630	140.886	79.910	60.693

Snapdragon 855	Anakin fp32			Anakin int8			NCNN fp32			NCNN int8
	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread
mobilenet_v1	34.015	20.064	11.410	42.222	21.532	11.746	41.150	24.870	18.420	79.180	48.470	24.530
mobilenet_v2	30.742	18.507	11.354	24.628	15.133	9.079	30.060	19.220	15.520
mobilenet_ssd	69.749	44.010	26.000				85.030	62.770	48.940	154.600	138.700	82.140
resnet50	218.581	146.509	92.899				1380.340	996.410	540.660	324.720	261.920	126.270
shufflenetv1	11.032	7.430	5.369				13.390	9.270	6.360
shufflenetv2	11.372	7.120	4.728	19.393	12.278	7.719
squeezenet	27.860	17.538	10.729
googlenet	100.719	69.509	49.021	127.982	83.369	50.275

Snapdragon 652	Anakin fp32			Anakin int8			NCNN fp32			NCNN int8
	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread	1 thread	2 thread	4 thread
mobilenet_v1	121.982	63.004	37.325	86.672	45.728	26.354	130.740	140.850	81.810	184.630	192.730	144.740
mobilenet_v2	89.113	50.609	35.291	72.679	45.888	33.887	94.520	101.380	65.570
mobilenet_ssd	236.466	132.293	86.335				270.630	295.520	174.280	350.640	286.420	243.850
resnet50	751.528	405.433	255.699				2762.890	1447.070	883.730	664.180	369.020
shufflenetv1	36.883	23.718	15.144				53.660	33.450	23.330
shufflenetv2	36.933	26.353	20.507	53.243	31.083	21.550
squeezenet	92.748	51.936	33.027
googlenet	296.092	179.542	125.509	242.505	140.083	89.646

RK3399	Anakin fp32		Anakin int8		NCNN fp32		NCNN int8
	1 thread	2 thread	1 thread	2 thread	1 thread	2 thread	1 thread	2 thread
mobilenet_v1	116.981	65.033	87.768	47.617	155.830	98.520	201.800	116.440
mobilenet_v2	118.229	70.567	83.790	55.413	126.530	90.930
mobilenet_ssd	237.196	134.508			292.130	183.650	361.570	200.370
resnet50	725.582	413.995			2883.120	1632.800	702.660	404.970
shufflenetv1	41.094	27.353
shufflenetv2	37.660	23.489	53.558	32.122
squeezenet	104.519	59.402
googlenet	305.304	190.897	244.855	142.493

Documentation

All you need is in Doc Index

We also provide English and Chinese tutorial documentation.

User guide

You can get the working principle of the project, C++ interface description and code examples from here. You can also learn about the model converter here.
Developer guide

You might want to know more details of Anakin and make it better. Please refer to how to add custom devices and how to add custom device operators.
How to Contribute

We appreciate your contributions!

Ask Questions

You are welcome to submit questions and bug reports as Github Issues.

Copyright and License

Anakin is provided under the Apache-2.0 license.

Acknowledgement

Anakin refers to the following projects:

anakin's People

Contributors

Stargazers

Watchers

Forkers

qq332982511 pangge chenjiaoangel littlemaer cyj1986 xyoungli wuhuikx shixiaowei02 blackzhengsq rkshuai chenqy4933 runauto nihui hooloong burness erichouyi jianlongf susyimes l1129433134 aaronyking phenixi keyky huajianni666 renfeier tao-githup chenzhenhua986 lsclone templeblock chybhao666 ychjiang lizhelong wangkaizjuzju loliod yingyingshin shenhzou654321 wgy0804 maziyang08 guangzhixie kzjeef k9sret alan-turing-ko cuihao19931030 tianylijun chenzj00 barongeng mengkai94 woisnow leiyu1980 throneclay hanchaow jiayanyuan mypandashaoxiang yiicy tinycodervs rocmsoftwareplatform jayoprell lowintelligence cooparation qichaotang kiritigowda xklnono strongerwill linecode zmsunnyday glorysdj flyingjeslee facegen luckyathuka wzzju yihuis huangjun6919 tuzhenyuan snailtowardthesun 2015-10-10 liuhd1992 jealous1989 zgsxwsdxg delongqilinksprite hlzy gitlp vladtimm zhbxlm zmoon111 hiker2046 suntaiwu greenfigo2015 shjwudp kagome112 alongneu queenwu yishengcheng pubfork tsingjinyun laoyingbu uraj xiaoguanghu01 kimxiao1119 jiangjiajun wgfi110 tidesq

anakin's Issues

请问 developing 分支和 dev_2 有什么区别？

请问 developing 分支和 dev_2 有什么区别？,我发现更新 dev_2 比 developing 要快

Improve exception safety with smart pointers

Would you like to wrap any pointers with the class template “std::unique_ptr”?

TensorRT MobileNet benchmark results

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?

load saved model failed

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 [??:?]

Will Windows be supported?

Hi,

Will Windows be supported?

Thanks

no example

no example for new user

[BUG] 7cdf32 commit

How to run in ios deveces？

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.

where can i get anakin_third_party.tar.gz?

Error while runtime ! Target attr name(weight_2) not found

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.

Dose libanakin_saber_sass_sm_61.a support fp16?

@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?

argmax compute error

Dockerfiles build error

Dockerfile can't be built successfully

Anakin docker build error on ubuntu 16.04 for Nvidia-GPU

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

使用external_converter_v2目录下的converter.py转换caffemodle模型失败

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

x86_build.s执行error

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

ubuntu build fail

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; }

wrong impl init

base.h has some wrong impl init.

convert tool error when convert caffe model

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'

改变输入尺寸

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？

convert tool failed caffe

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.

saber_normalize occasionally wrong result when param.across_spatial=true

build faild when USE X86 OFF

download third party labraries when make the project

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.

Support and benchmark for int8

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!

need embedding and scale op

GCC 7.2.0 build request.h error

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); }

Anakin Can't build with mklml...

Wrong calculation in pooling layer. < pooling3x3s2_max >

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.

gpu multi-stream sync error

tensores are not synced when ops are launched in different streams

ubuntu 16.04 build fail on gcc 4.8.5

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

only debug mode can work

when I complied with release flag, benchmark will exit with segment fault, but debug will be ok

how to run model on android device

where are the head files?

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"

Remove unnecessary null pointer checks

An extra null pointer check is not needed in functions like the following.

Anakin arm branch: run squeezenet_v1.1, result is all zero!!!

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 !!!

Wrong shape of input tensor.

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.

how to set gpu id

seems it uses all gpus, is there a way to specify one?

编译错误

使用脚本编译Anakin Lite库，直接运行lite_ios_build_armv7/8.sh，出现很多error

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

build failed on Centos

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

Crash when Optimize Graph?

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];
}

使用external_converter_v2目录下的converter.py转换mobilenet-ssd的caffemodle模型失败

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!

Support for different input shapes between frames

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~ ~

Could NOT find OpenMP_C on mac

How to bind net on specific GPU id

how to set gpu id ?

reserved identifier violation

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?

How to build the ios anakin from source ?

Thanks, I can only find the android build tutorial in your doc.

has opencl(ARMGPU ) supported now?

Help!! Crash in Net init.

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.

paddlepaddle / anakin Goto Github PK

anakin's Introduction

Anakin2.0

Features

NV GPU Benchmark

Machine And Enviornment

VGG16

Resnet50

Resnet101

X86 CPU Benchmark

Machine And Enviornment

ARM CPU Benchmark

Machine And Enviornment

ARMv8 TEST

ARMv7 TEST

Documentation

Ask Questions

Copyright and License

Acknowledgement

anakin's People

Contributors

Stargazers

Watchers

Forkers

anakin's Issues

Recommend Projects

Recommend Topics

Recommend Org