| 1）cat /proc/cpuinfo processor : 79 vendor_id : GenuineIntel cpu family : 6 model : 85 model name : Intel(R) Xeon(R) Gold 6248 CPU @ 2.50GHz stepping : 7 microcode : 0x5000024 cpu MHz : 1000.213 cache size : 28160 KB physical id : 1 siblings : 40 core id : 28 cpu cores : 20 apicid : 121 initial apicid : 121 fpu : yes fpu_exception : yes cpuid level : 22 wp : yes 2）默认参数 GPU=0 CUDNN=0 OPENCV=0 OPENMP=0 DEBUG=0 3） 生成了库和可招待文件 backup darknet examples libdarknet.a LICENSE LICENSE.gen LICENSE.meta LICENSE.v1 obj README.md scripts cfg data include libdarknet.so LICENSE.fuck LICENSE.gpl LICENSE.mit Makefile python results src 好像还缺少模型文件 4）下载文件 运行命令 4）出错了 [Thread debugging using libthread_db enabled] Using host libthread_db library "/lib64/libthread_db.so.1". Program received signal SIGSEGV, Segmentation fault. 0x0000000000460908 in read_cfg (filename=0x7fffffffc5fb "model/yolov3-tiny.cfg") at ./src/parser.c:915 915 if(!read_option(line, current->options)){ Missing separate debuginfos, use: debuginfo-install glibc-2.17-222.el7.x86_64 (gdb) bt #0 0x0000000000460908 in read_cfg (filename=0x7fffffffc5fb "model/yolov3-tiny.cfg") at ./src/parser.c:915 #1 0x000000000045f7a2 in parse_network_cfg (filename=0x7fffffffc5fb "model/yolov3-tiny.cfg") at ./src/parser.c:744 #2 0x00000000004583bf in load_network (cfg=0x7fffffffc5fb "model/yolov3-tiny.cfg", weights=0x7fffffffc611 "model/yolov3-tiny.weights", clear=0) at ./src/network.c:55 #3 0x000000000041bf3b in test_detector (datacfg=0x47be74 "cfg/coco.data", cfgfile=0x7fffffffc5fb "model/yolov3-tiny.cfg", weightfile=0x7fffffffc611 "model/yolov3-tiny.weights", filename=0x7fffffffc62b "data/dog.jpg", thresh=0.5, hier_thresh=0.5, outfile=0x0, fullscreen=0) at ./examples/detector.c:569 #4 0x00000000004216a0 in main (argc=5, argv=0x7fffffffc0f8) at ./examples/darknet.c:437 4)读cfg文件出错， 查看了一下，确实有问题： <!DOCTYPE html> <html lang="en" data-color-mode="auto" data-light-theme="light" data-dark-theme="dark" data-a11y-animated-images="system" data-a11y-link-underlines="false"> <style> /* for each iteration, uncomment the CSS variable */ /* light themes */ [data-color-mode="light"][data-light-theme*="light"], [data-color-mode="auto"][data-light-theme*="light"] { /* iteration 1 */ --border-color-iteration-1: #C8CCD0; /* iteration 2 */ --border-color-iteration-2: #BABFC5; /* iteration 3 */ 5）换自带的CFG就OK了 ./darknet detect cfg/yolov3-tiny.cfg model/yolov3-tiny.weights data/dog.jpg layer filters size input output 0 conv 16 3 x 3 / 1 416 x 416 x 3 -> 416 x 416 x 16 0.150 BFLOPs 1 max 2 x 2 / 2 416 x 416 x 16 -> 208 x 208 x 16 2 conv 32 3 x 3 / 1 208 x 208 x 16 -> 208 x 208 x 32 0.399 BFLOPs 3 max 2 x 2 / 2 208 x 208 x 32 -> 104 x 104 x 32 4 conv 64 3 x 3 / 1 104 x 104 x 32 -> 104 x 104 x 64 0.399 BFLOPs 5 max 2 x 2 / 2 104 x 104 x 64 -> 52 x 52 x 64 6 conv 128 3 x 3 / 1 52 x 52 x 64 -> 52 x 52 x 128 0.399 BFLOPs 7 max 2 x 2 / 2 52 x 52 x 128 -> 26 x 26 x 128 8 conv 256 3 x 3 / 1 26 x 26 x 128 -> 26 x 26 x 256 0.399 BFLOPs 9 max 2 x 2 / 2 26 x 26 x 256 -> 13 x 13 x 256 10 conv 512 3 x 3 / 1 13 x 13 x 256 -> 13 x 13 x 512 0.399 BFLOPs 11 max 2 x 2 / 1 13 x 13 x 512 -> 13 x 13 x 512 12 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs 13 conv 256 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 256 0.089 BFLOPs 14 conv 512 3 x 3 / 1 13 x 13 x 256 -> 13 x 13 x 512 0.399 BFLOPs 15 conv 255 1 x 1 / 1 13 x 13 x 512 -> 13 x 13 x 255 0.044 BFLOPs 16 yolo 6) In file included from ./src/utils.h:5:0, from ./src/gemm.c:2: include/darknet.h:11:30: 致命错误：cuda_runtime.h：没有那个文件或目录 #include "cuda_runtime.h" 通过修改Makefile中的标记解决 7） gcc -Iinclude/ -Isrc/ -DGPU -I/public/software/cuda-11.4.3/include/ -Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC -fopenmp -Ofast -DGPU -c ./src/l2norm_layer.c -o obj/l2norm_layer.o gcc -Iinclude/ -Isrc/ -DGPU -I/public/software/cuda-11.4.3/include/ -Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC -fopenmp -Ofast -DGPU -c ./src/yolo_layer.c -o obj/yolo_layer.o gcc -Iinclude/ -Isrc/ -DGPU -I/public/software/cuda-11.4.3/include/ -Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC -fopenmp -Ofast -DGPU -c ./src/iseg_layer.c -o obj/iseg_layer.o g++ -Iinclude/ -Isrc/ -DGPU -I/public/software/cuda-11.4.3/include/ -Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC -fopenmp -Ofast -DGPU -c ./src/image_opencv.cpp -o obj/image_opencv.o nvcc -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=[sm_50,compute_50] -gencode arch=compute_52,code=[sm_52,compute_52] -Iinclude/ -Isrc/ -DGPU -I/public/software/cuda-11.4.3/include/ --compiler-options "-Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC -fopenmp -Ofast -DGPU" -c ./src/convolutional_kernels.cu -o obj/convolutional_kernels.o nvcc fatal : Unsupported gpu architecture 'compute_30' make: *** [obj/convolutional_kernels.o] 错误 1 8） --gres=gpu:1 ./darknet usage: /public/home/hpc221051/z1.gon/14-deeplearning/d1.darknet-master.CPU/./darknet <function> (base) [hpc221051@ln03 d1.darknet-master.CPU]$ srun -n 1 -A pi_xhk -p gpu2Q -q gpuq --gres=gpu:1 ./darknet detect cfg/yolov3-tiny.cfg model/yolov3-tiny.weights data/dog.jpg layer filters size input output 0 conv 16 3 x 3 / 1 416 x 416 x 3 -> 416 x 416 x 16 0.150 BFLOPs 1 max 2 x 2 / 2 416 x 416 x 16 -> 208 x 208 x 16 2 conv 32 3 x 3 / 1 208 x 208 x 16 -> 208 x 208 x 32 0.399 BFLOPs 3 max 2 x 2 / 2 208 x 208 x 32 -> 104 x 104 x 32 4 conv 64 3 x 3 / 1 104 x 104 x 32 -> 104 x 104 x 64 0.399 BFLOPs 5 max 2 x 2 / 2 104 x 104 x 64 -> 52 x 52 x 64 6 conv 128 3 x 3 / 1 52 x 52 x 64 -> 52 x 52 x 128 0.399 BFLOPs 7 max 2 x 2 / 2 52 x 52 x 128 -> 26 x 26 x 128 8 conv 256 3 x 3 / 1 26 x 26 x 128 -> 26 x 26 x 256 0.399 BFLOPs 可以跑，但是太慢了 |
说点什么...