'잡동사니'에 해당되는 글 13388건

  1. 2021.01.09 CNN과 RNN
  2. 2021.01.09 darknet과 darknetab
  3. 2021.01.09 세탁기가 얼다니!!
  4. 2021.01.08 제노블레이드 크로니클스 de 엔딩
  5. 2021.01.08 darknet openmp 빌드
  6. 2021.01.08 i.mx6quad용 gcc 옵션
  7. 2021.01.08 darknet on rpi3
  8. 2021.01.08 yolo lite
  9. 2021.01.08 SSDnnn (Single Shot Detector)
  10. 2021.01.08 segmentation fault, bus error
프로그램 사용/yolo_tensorflow2021. 1. 9. 17:31

CNN과 RNN

RNN(Recurrent Neural Network)

 

CNN(Convolution Neural Network)

합성곱신경망, convolution과 pooling

 

[링크 : http://ebbnflow.tistory.com/119]

[링크 : http://dbrang.tistory.com/1537]

 

저작자표시

'프로그램 사용 > yolo_tensorflow' 카테고리의 다른 글

darknet detect  (0) 2021.01.11
CNN convolution과 maxpool  (0) 2021.01.10
darknet과 darknetab  (0) 2021.01.09
darknet openmp 빌드  (0) 2021.01.08
darknet on rpi3  (0) 2021.01.08
Posted by 구차니
프로그램 사용/yolo_tensorflow2021. 1. 9. 16:46

darknet과 darknetab

원본 darknet은 성능에 영향을 줄게 3개 밖에 없는데

GPU=0
CUDNN=0
OPENCV=0
OPENMP=0

 

alexeyAB의 darknet은 gpu, cudnn, avx, openmp 4가지 이다.

GPU=0
CUDNN=0
CUDNN_HALF=0
OPENCV=0
AVX=0
OPENMP=0
LIBSO=0
ZED_CAMERA=0
ZED_CAMERA_v2_8=0

[링크 : https://github.com/AlexeyAB/darknet]

 

심심해서(?) i5-2세대도 있나 보는데 어라..? 있네?

[링크 : https://ark.intel.com/.../intel-core-i5-2500-processor-6m-cache-up-to-3-70-ghz.html]

[링크 : https://ark.intel.com/../intel-core-i5-2520m-processor-3m-cache-up-to-3-20-ghz.html]

 

근데 빌드해서 돌려보니 내꺼는 AVX일뿐이라 돌아가지 않는다 ㅠㅠ

AVX2는 하스웰 이후부터 지원한다고 하니.. 집에있는 내 실험용 컴퓨터로는 무리겠구나..

$ ./darknet detect cfg/yolov3.cfg ../yolov3.weights data/dog.jpg
 GPU isn't used 
 Used AVX 
 Not used FMA & AVX2 
 OpenCV isn't used - data augmentation will be slow 
명령어가 잘못됨 (core dumped)

 

alexeyAB 버전을 싱글 코어 / openmp 설정으로 돌리니 반정도 줄었다.

data/dog.jpg: Predicted in 11175.292000 milli-seconds.
data/dog.jpg: Predicted in 5974.575000 milli-seconds.
저작자표시

'프로그램 사용 > yolo_tensorflow' 카테고리의 다른 글

CNN convolution과 maxpool  (0) 2021.01.10
CNN과 RNN  (0) 2021.01.09
darknet openmp 빌드  (0) 2021.01.08
darknet on rpi3  (0) 2021.01.08
yolo lite  (0) 2021.01.08
Posted by 구차니
개소리 왈왈/육아관련 주저리2021. 1. 9. 11:09

세탁기가 얼다니!!

아침 일어나니 -22도!!!

점심때나 되니 -11도

영하 20도를 넘나드니 영하10도는 따스한 착각마저 드네 ㅋㅋ

저작자표시

'개소리 왈왈 > 육아관련 주저리' 카테고리의 다른 글

UHD 프로그램이 별로 없네  (0) 2021.01.17
1인 사우나를 샀다 그리고 핸드폰을 빼앗겼다  (0) 2021.01.15
오늘 최고기온 -10도  (4) 2021.01.07
새가 졸리면 하는 행동?  (0) 2021.01.02
2021년 새해!  (0) 2021.01.01
Posted by 구차니
게임/닌텐도 스위치2021. 1. 8. 23:23

제노블레이드 크로니클스 de 엔딩

100시간은 족히 한듯

아무튼 그 와중에 제노블레이드 크로니클스2 살려고 기웃대고 있고

 

DLC라고 해야하나? "이어지는 미래"도 해야하는데

시작해보니 60렙부터 시작하는군 ㅋ

저작자표시

'게임 > 닌텐도 스위치' 카테고리의 다른 글

제노블레이드 공략  (0) 2021.03.28
닌텐도 스위치 왼쪽 조이스틱 또 고장  (0) 2021.01.31
조이콘 조이스틱 부품 분해  (0) 2020.12.14
조이콘 수리  (4) 2020.12.12
닌텐도 스위치 보호필름 교체 그리고 조이콘 조이스틱 수리  (0) 2020.12.12
Posted by 구차니
프로그램 사용/yolo_tensorflow2021. 1. 8. 18:01

darknet openmp 빌드

위는 오리지널 darknet을 아무런 옵션없이 라즈베리에서 빌드한 결과

$ ldd darknet
        linux-vdso.so.1 (0x7efe1000)
        /usr/lib/arm-linux-gnueabihf/libarmmem-${PLATFORM}.so => /usr/lib/arm-linux-gnueabihf/libarmmem-v7l.so (0x76f54000)
        libm.so.6 => /lib/arm-linux-gnueabihf/libm.so.6 (0x76eb6000)
        libpthread.so.0 => /lib/arm-linux-gnueabihf/libpthread.so.0 (0x76e8c000)
        libc.so.6 => /lib/arm-linux-gnueabihf/libc.so.6 (0x76d3e000)
        /lib/ld-linux-armhf.so.3 (0x76f69000)

 

아래는 darknet AlexeyAB 버전을 neon과 openmp 설정해서 빌드한 결과

$ ldd darknet
        linux-vdso.so.1 (0x7eefc000)
        /usr/lib/arm-linux-gnueabihf/libarmmem-${PLATFORM}.so => /usr/lib/arm-linux-gnueabihf/libarmmem-v7l.so (0x76f79000)
        libgomp.so.1 => /lib/arm-linux-gnueabihf/libgomp.so.1 (0x76f25000)
        libstdc++.so.6 => /lib/arm-linux-gnueabihf/libstdc++.so.6 (0x76dde000)
        libm.so.6 => /lib/arm-linux-gnueabihf/libm.so.6 (0x76d5c000)
        libgcc_s.so.1 => /lib/arm-linux-gnueabihf/libgcc_s.so.1 (0x76d2f000)
        libpthread.so.0 => /lib/arm-linux-gnueabihf/libpthread.so.0 (0x76d05000)
        libc.so.6 => /lib/arm-linux-gnueabihf/libc.so.6 (0x76bb7000)
        libdl.so.2 => /lib/arm-linux-gnueabihf/libdl.so.2 (0x76ba4000)
        /lib/ld-linux-armhf.so.3 (0x76f8e000)

 

 

+

cpu only = 30.13sec

$ ./tiny.sh
 GPU isn't used
 OpenCV isn't used - data augmentation will be slow
mini_batch = 1, batch = 1, time_steps = 1, train = 0
   layer   filters  size/strd(dil)      input                output
   0 conv     16       3 x 3/ 1    416 x 416 x   3 ->  416 x 416 x  16 0.150 BF
   1 max                2x 2/ 2    416 x 416 x  16 ->  208 x 208 x  16 0.003 BF
   2 conv     32       3 x 3/ 1    208 x 208 x  16 ->  208 x 208 x  32 0.399 BF
   3 max                2x 2/ 2    208 x 208 x  32 ->  104 x 104 x  32 0.001 BF
   4 conv     64       3 x 3/ 1    104 x 104 x  32 ->  104 x 104 x  64 0.399 BF
   5 max                2x 2/ 2    104 x 104 x  64 ->   52 x  52 x  64 0.001 BF
   6 conv    128       3 x 3/ 1     52 x  52 x  64 ->   52 x  52 x 128 0.399 BF
   7 max                2x 2/ 2     52 x  52 x 128 ->   26 x  26 x 128 0.000 BF
   8 conv    256       3 x 3/ 1     26 x  26 x 128 ->   26 x  26 x 256 0.399 BF
   9 max                2x 2/ 2     26 x  26 x 256 ->   13 x  13 x 256 0.000 BF
  10 conv    512       3 x 3/ 1     13 x  13 x 256 ->   13 x  13 x 512 0.399 BF
  11 max                2x 2/ 1     13 x  13 x 512 ->   13 x  13 x 512 0.000 BF
  12 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  13 conv    256       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 256 0.089 BF
  14 conv    512       3 x 3/ 1     13 x  13 x 256 ->   13 x  13 x 512 0.399 BF
  15 conv    255       1 x 1/ 1     13 x  13 x 512 ->   13 x  13 x 255 0.044 BF
  16 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.00
  17 route  13                                     ->   13 x  13 x 256
  18 conv    128       1 x 1/ 1     13 x  13 x 256 ->   13 x  13 x 128 0.011 BF
  19 upsample                 2x    13 x  13 x 128 ->   26 x  26 x 128
  20 route  19 8                                   ->   26 x  26 x 384
  21 conv    256       3 x 3/ 1     26 x  26 x 384 ->   26 x  26 x 256 1.196 BF
  22 conv    255       1 x 1/ 1     26 x  26 x 256 ->   26 x  26 x 255 0.088 BF
  23 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.00
Total BFLOPS 5.571
avg_outputs = 341534
Loading weights from ../yolov3-tiny.weights...
 seen 64, trained: 32013 K-images (500 Kilo-batches_64)
Done! Loaded 24 layers from weights-file
 Detection layer: 16 - type = 28
 Detection layer: 23 - type = 28
data/dog.jpg: Predicted in 30133.750000 milli-seconds.
dog: 81%
bicycle: 38%
car: 71%
truck: 42%
truck: 62%
car: 40%
Not compiled with OpenCV, saving to predictions.png instead

 

neon = 10.718 sec

$ ./tiny.sh
 GPU isn't used
 OpenCV isn't used - data augmentation will be slow
mini_batch = 1, batch = 1, time_steps = 1, train = 0
   layer   filters  size/strd(dil)      input                output
   0 conv     16       3 x 3/ 1    416 x 416 x   3 ->  416 x 416 x  16 0.150 BF
   1 max                2x 2/ 2    416 x 416 x  16 ->  208 x 208 x  16 0.003 BF
   2 conv     32       3 x 3/ 1    208 x 208 x  16 ->  208 x 208 x  32 0.399 BF
   3 max                2x 2/ 2    208 x 208 x  32 ->  104 x 104 x  32 0.001 BF
   4 conv     64       3 x 3/ 1    104 x 104 x  32 ->  104 x 104 x  64 0.399 BF
   5 max                2x 2/ 2    104 x 104 x  64 ->   52 x  52 x  64 0.001 BF
   6 conv    128       3 x 3/ 1     52 x  52 x  64 ->   52 x  52 x 128 0.399 BF
   7 max                2x 2/ 2     52 x  52 x 128 ->   26 x  26 x 128 0.000 BF
   8 conv    256       3 x 3/ 1     26 x  26 x 128 ->   26 x  26 x 256 0.399 BF
   9 max                2x 2/ 2     26 x  26 x 256 ->   13 x  13 x 256 0.000 BF
  10 conv    512       3 x 3/ 1     13 x  13 x 256 ->   13 x  13 x 512 0.399 BF
  11 max                2x 2/ 1     13 x  13 x 512 ->   13 x  13 x 512 0.000 BF
  12 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  13 conv    256       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 256 0.089 BF
  14 conv    512       3 x 3/ 1     13 x  13 x 256 ->   13 x  13 x 512 0.399 BF
  15 conv    255       1 x 1/ 1     13 x  13 x 512 ->   13 x  13 x 255 0.044 BF
  16 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.00
  17 route  13                                     ->   13 x  13 x 256
  18 conv    128       1 x 1/ 1     13 x  13 x 256 ->   13 x  13 x 128 0.011 BF
  19 upsample                 2x    13 x  13 x 128 ->   26 x  26 x 128
  20 route  19 8                                   ->   26 x  26 x 384
  21 conv    256       3 x 3/ 1     26 x  26 x 384 ->   26 x  26 x 256 1.196 BF
  22 conv    255       1 x 1/ 1     26 x  26 x 256 ->   26 x  26 x 255 0.088 BF
  23 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.00
Total BFLOPS 5.571
avg_outputs = 341534
Loading weights from ../yolov3-tiny.weights...
 seen 64, trained: 32013 K-images (500 Kilo-batches_64)
Done! Loaded 24 layers from weights-file
 Detection layer: 16 - type = 28
 Detection layer: 23 - type = 28
data/dog.jpg: Predicted in 10718.416000 milli-seconds.
dog: 81%
bicycle: 38%
car: 71%
truck: 42%
truck: 62%
car: 40%
Not compiled with OpenCV, saving to predictions.png instead

 

openmp = 8.686 sec

$ ./tiny.sh
 GPU isn't used
 OpenCV isn't used - data augmentation will be slow
mini_batch = 1, batch = 1, time_steps = 1, train = 0
   layer   filters  size/strd(dil)      input                output
   0 conv     16       3 x 3/ 1    416 x 416 x   3 ->  416 x 416 x  16 0.150 BF
   1 max                2x 2/ 2    416 x 416 x  16 ->  208 x 208 x  16 0.003 BF
   2 conv     32       3 x 3/ 1    208 x 208 x  16 ->  208 x 208 x  32 0.399 BF
   3 max                2x 2/ 2    208 x 208 x  32 ->  104 x 104 x  32 0.001 BF
   4 conv     64       3 x 3/ 1    104 x 104 x  32 ->  104 x 104 x  64 0.399 BF
   5 max                2x 2/ 2    104 x 104 x  64 ->   52 x  52 x  64 0.001 BF
   6 conv    128       3 x 3/ 1     52 x  52 x  64 ->   52 x  52 x 128 0.399 BF
   7 max                2x 2/ 2     52 x  52 x 128 ->   26 x  26 x 128 0.000 BF
   8 conv    256       3 x 3/ 1     26 x  26 x 128 ->   26 x  26 x 256 0.399 BF
   9 max                2x 2/ 2     26 x  26 x 256 ->   13 x  13 x 256 0.000 BF
  10 conv    512       3 x 3/ 1     13 x  13 x 256 ->   13 x  13 x 512 0.399 BF
  11 max                2x 2/ 1     13 x  13 x 512 ->   13 x  13 x 512 0.000 BF
  12 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  13 conv    256       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 256 0.089 BF
  14 conv    512       3 x 3/ 1     13 x  13 x 256 ->   13 x  13 x 512 0.399 BF
  15 conv    255       1 x 1/ 1     13 x  13 x 512 ->   13 x  13 x 255 0.044 BF
  16 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.00
  17 route  13                                     ->   13 x  13 x 256
  18 conv    128       1 x 1/ 1     13 x  13 x 256 ->   13 x  13 x 128 0.011 BF
  19 upsample                 2x    13 x  13 x 128 ->   26 x  26 x 128
  20 route  19 8                                   ->   26 x  26 x 384
  21 conv    256       3 x 3/ 1     26 x  26 x 384 ->   26 x  26 x 256 1.196 BF
  22 conv    255       1 x 1/ 1     26 x  26 x 256 ->   26 x  26 x 255 0.088 BF
  23 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.00
Total BFLOPS 5.571
avg_outputs = 341534
Loading weights from ../yolov3-tiny.weights...
 seen 64, trained: 32013 K-images (500 Kilo-batches_64)
Done! Loaded 24 layers from weights-file
 Detection layer: 16 - type = 28
 Detection layer: 23 - type = 28
data/dog.jpg: Predicted in 8686.237000 milli-seconds.
dog: 81%
bicycle: 38%
car: 71%
truck: 42%
truck: 62%
car: 40%
Not compiled with OpenCV, saving to predictions.png instead

 

 

openmp + neon = 4.449 sec

$ ./tiny.sh
 GPU isn't used
 OpenCV isn't used - data augmentation will be slow
mini_batch = 1, batch = 1, time_steps = 1, train = 0
   layer   filters  size/strd(dil)      input                output
   0 conv     16       3 x 3/ 1    416 x 416 x   3 ->  416 x 416 x  16 0.150 BF
   1 max                2x 2/ 2    416 x 416 x  16 ->  208 x 208 x  16 0.003 BF
   2 conv     32       3 x 3/ 1    208 x 208 x  16 ->  208 x 208 x  32 0.399 BF
   3 max                2x 2/ 2    208 x 208 x  32 ->  104 x 104 x  32 0.001 BF
   4 conv     64       3 x 3/ 1    104 x 104 x  32 ->  104 x 104 x  64 0.399 BF
   5 max                2x 2/ 2    104 x 104 x  64 ->   52 x  52 x  64 0.001 BF
   6 conv    128       3 x 3/ 1     52 x  52 x  64 ->   52 x  52 x 128 0.399 BF
   7 max                2x 2/ 2     52 x  52 x 128 ->   26 x  26 x 128 0.000 BF
   8 conv    256       3 x 3/ 1     26 x  26 x 128 ->   26 x  26 x 256 0.399 BF
   9 max                2x 2/ 2     26 x  26 x 256 ->   13 x  13 x 256 0.000 BF
  10 conv    512       3 x 3/ 1     13 x  13 x 256 ->   13 x  13 x 512 0.399 BF
  11 max                2x 2/ 1     13 x  13 x 512 ->   13 x  13 x 512 0.000 BF
  12 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  13 conv    256       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 256 0.089 BF
  14 conv    512       3 x 3/ 1     13 x  13 x 256 ->   13 x  13 x 512 0.399 BF
  15 conv    255       1 x 1/ 1     13 x  13 x 512 ->   13 x  13 x 255 0.044 BF
  16 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.00
  17 route  13                                     ->   13 x  13 x 256
  18 conv    128       1 x 1/ 1     13 x  13 x 256 ->   13 x  13 x 128 0.011 BF
  19 upsample                 2x    13 x  13 x 128 ->   26 x  26 x 128
  20 route  19 8                                   ->   26 x  26 x 384
  21 conv    256       3 x 3/ 1     26 x  26 x 384 ->   26 x  26 x 256 1.196 BF
  22 conv    255       1 x 1/ 1     26 x  26 x 256 ->   26 x  26 x 255 0.088 BF
  23 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.00
Total BFLOPS 5.571
avg_outputs = 341534
Loading weights from ../yolov3-tiny.weights...
 seen 64, trained: 32013 K-images (500 Kilo-batches_64)
Done! Loaded 24 layers from weights-file
 Detection layer: 16 - type = 28
 Detection layer: 23 - type = 28
data/dog.jpg: Predicted in 4449.888000 milli-seconds.
dog: 81%
bicycle: 38%
car: 71%
truck: 42%
truck: 62%
car: 40%
Not compiled with OpenCV, saving to predictions.png instead

 

저작자표시

'프로그램 사용 > yolo_tensorflow' 카테고리의 다른 글

CNN과 RNN  (0) 2021.01.09
darknet과 darknetab  (0) 2021.01.09
darknet on rpi3  (0) 2021.01.08
yolo lite  (0) 2021.01.08
SSDnnn (Single Shot Detector)  (0) 2021.01.08
Posted by 구차니
embeded2021. 1. 8. 17:59

i.mx6quad용 gcc 옵션

아래의 옵션을 추천해서 적용해 보았는데

-mthumb -O3 -march=armv7-a -mcpu=cortex-a9 -mtune=cortex-a9 -mfpu=neon -mvectorize-with-neon-quad -mfloat-abi=softfp

[링크 : https://stackoverflow.com/questions/14962447/gcc-options-for-a-freescale-imx6q-arm-processor]

[링크 : https://gcc.gnu.org/onlinedocs/gcc/ARM-Options.html]

 

에러가 나서 mfloat-abi=softfp 에서 hard로 변경

In file included from /usr/include/features.h:448,
                 from /usr/include/arm-linux-gnueabihf/bits/libc-header-start.h:33,
                 from /usr/include/stdlib.h:25,
                 from include/darknet.h:12,
                 from ./src/activations.h:3,
                 from ./src/gemm.h:3,
                 from ./src/gemm.c:1:
/usr/include/arm-linux-gnueabihf/gnu/stubs.h:7:11: fatal error: gnu/stubs-soft.h: No such file or directory
 # include <gnu/stubs-soft.h>
           ^~~~~~~~~~~~~~~~~~
compilation terminated.

[링크 : https://stackoverflow.com/questions/49139125/fatal-error-gnu-stubs-soft-h-no-such-file-or-directory]

 

아무튼 빌드는 되지만 아래와 같은 경고가 뜬다. march와 mcpu가 충돌난다라.. 어느걸 살려야 할까?

cc1: warning: switch -mcpu=cortex-a9 conflicts with -march=armv7-a switch

 

 

+

2021.01.12

[링크 : https://developer.arm.com/documentation/dui0472/i/using-the-neon-vectorizing-compiler/generating-neon-instructions-from-c-or-c---code]

 

저작자표시

'embeded' 카테고리의 다른 글

중고 부품 지름  (0) 2025.01.06
arm-none-eabi는 -pthread 미지원  (0) 2021.01.11
orange pi r1+  (0) 2021.01.08
i.mx6 solo 비디오 성능 문제?  (0) 2020.10.19
간만에 부품 지름  (2) 2020.03.04
Posted by 구차니
프로그램 사용/yolo_tensorflow2021. 1. 8. 16:39

darknet on rpi3

원인 불명으로 BUS error나 Segmentation fault가 떠서 찾아보니

소스를 수정한 버전이 있다고 한다.

돌아는 가는데.... (이하 생략)

 

[링크 : https://j-remind.tistory.com/53]

[링크 : https://github.com/AlexeyAB/darknet]

 

설마 endian 문제?

[링크 : https://github.com/pjreddie/darknet/issues/823]

저작자표시

'프로그램 사용 > yolo_tensorflow' 카테고리의 다른 글

darknet과 darknetab  (0) 2021.01.09
darknet openmp 빌드  (0) 2021.01.08
yolo lite  (0) 2021.01.08
SSDnnn (Single Shot Detector)  (0) 2021.01.08
CNN - YOLO  (0) 2021.01.07
Posted by 구차니
프로그램 사용/yolo_tensorflow2021. 1. 8. 16:05

yolo lite

YOLOv2-tiny 의 web implementation 이라는데 웹 implementation이 머지?

 

[링크 : https://reu2018dl.github.io/]

[링크 : https://github.com/reu2018DL/YOLO-LITE]

[링크 : https://arxiv.org/pdf/1811.05588.pdf]

 

 

+

MS COCO 2014 and PASCAL VOC 2007 + 2012

 

pascal voc(Visual Object Classes)

[링크 : http://host.robots.ox.ac.uk/pascal/VOC/]

[링크 : https://ndb796.tistory.com/500]

 

MS COCO

COCO랑은 다른가?

[링크 : https://arxiv.org/pdf/1405.0312.pdf]

[링크 : https://chacha95.github.io/2020-02-27-Object-Detection4/]

[링크 : https://cocodataset.org/#home]

 

AP - Average Precision

mAP (mean AP)

[링크 : https://mezzaninex.tistory.com/entry/AI-COCO-Dataset-mAPmean-Average-Precision]

저작자표시

'프로그램 사용 > yolo_tensorflow' 카테고리의 다른 글

darknet openmp 빌드  (0) 2021.01.08
darknet on rpi3  (0) 2021.01.08
SSDnnn (Single Shot Detector)  (0) 2021.01.08
CNN - YOLO  (0) 2021.01.07
yolo BFLOPs  (0) 2020.10.21
Posted by 구차니
프로그램 사용/yolo_tensorflow2021. 1. 8. 16:01

SSDnnn (Single Shot Detector)

SSD 도 모델이군..

 

[링크 : https://pjreddie.com/darknet/yolo/]

[링크 : https://junjiwon1031.github.io/2017/09/08/Single-Shot-Multibox-Detector.html]

저작자표시

'프로그램 사용 > yolo_tensorflow' 카테고리의 다른 글

darknet on rpi3  (0) 2021.01.08
yolo lite  (0) 2021.01.08
CNN - YOLO  (0) 2021.01.07
yolo BFLOPs  (0) 2020.10.21
yolo3 on ubuntu 18.04  (0) 2020.10.20
Posted by 구차니
Linux2021. 1. 8. 15:58

segmentation fault, bus error

segmentation fault는 주소 영역은 존재하는데 접근해서는 안되는 주소를 간거라고 한다면

bus error는 물리적 주소조차도 존재하지 않는 영역을 갈경우 발생하는건가?

 

A Bus Errors triggers a process-level exception,notifying an  operating system(OS) that a process is trying to access memory that the CPU cannot physically address which in UNIX translates into a “SIGBUS” signal, which if not caught, will terminate the current process.

[링크 : https://learntechway.com/difference-between-segmentation-fault-and-bus-error/]

저작자표시

'Linux' 카테고리의 다른 글

특정 버전의 파일로 링크걸어서 빌드하기  (0) 2021.01.12
libc static build 하기  (0) 2021.01.12
linux ip 와 gateway 설정  (0) 2021.01.08
udev  (0) 2021.01.05
uio - userspace io  (0) 2021.01.05
Posted by 구차니

티스토리툴바