TVM上YOLO-DarkNet的部署已经在之前的文章TVM上部署YOLO-DarkNet及单图性能对比中介绍了。在单图测试结果中，TVM的速度提升约为1.27x。测出的时间数据显示，TVM测试代码中的STAGE1，也就是将模型导入Relay、编译模型的阶段是耗时最长的部分，而导入检测图片和执行检测图片的过程耗时较少。于是本文进一步使用多张图片进行测试。
第一部分 不使用TVM运行YOLO-DarkNet
YOLO-DarkNet的环境配置已经在之前的文章中介绍了。
之前讲到，运用YOLO进行单张图片检测的命令是：
./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg
如果要进行多张图片检测的话，需要对程序进行修改，实现批量测试图片并保存在自定义文件夹下，主要修改的是examples目录下的detector.c文件。
第一步，用下面的代码替换detector.c中的test_detector函数，请注意有三处路径需要改成自己的路径：
void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh, char *outfile, int fullscreen)
{
list *options = read_data_cfg(datacfg);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
image **alphabet = load_alphabet();
network *net = load_network(cfgfile, weightfile, 0);
set_batch_network(net, 1);
srand(2222222);
double time;
char buff[256];
char *input = buff;
float nms=.45;
int i=0;
while(1){
if(filename){
strncpy(input, filename, 256);
image im = load_image_color(input,0,0);
image sized = letterbox_image(im, net->w, net->h);
//image sized = resize_image(im, net->w, net->h);
//image sized2 = resize_max(im, net->w);
//image sized = crop_image(sized2, -((net->w - sized2.w)/2), -((net->h - sized2.h)/2), net->w, net->h);
//resize_network(net, sized.w, sized.h);
layer l = net->layers[net->n-1];
float *X = sized.data;
time=what_time_is_it_now();
network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, what_time_is_it_now()-time);
int nboxes = 0;
detection *dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, 0, 1, &nboxes);
//printf("%d\n", nboxes);
//if (nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
if (nms) do_nms_sort(dets, nboxes, l.classes, nms);
draw_detections(im, dets, nboxes, thresh, names, alphabet, l.classes);
free_detections(dets, nboxes);
if(outfile)
{
save_image(im, outfile);
}
else{
save_image(im, "predictions");
#ifdef OPENCV
cvNamedWindow("predictions", CV_WINDOW_NORMAL);
if(fullscreen){
cvSetWindowProperty("predictions", CV_WND_PROP_FULLSCREEN, CV_WINDOW_FULLSCREEN);
}
show_image(im, "predictions");
cvWaitKey(0);
cvDestroyAllWindows();
#endif
}
free_image(im);
free_image(sized);
if (filename) break;
}
else {
printf("Enter Image Path: ");
fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
list *plist = get_paths(input);
char **paths = (char **)list_to_array(plist);
printf("Start Testing!\n");
int m = plist->size;
if(access("/home/ztj/tvm/darknet/data/multi/out",0)==-1)//要改成自己的输出路径
{
if (mkdir("/home/ztj/tvm/darknet/data/multi/out",0777))//要改成自己的输出路径
{
printf("creat file bag failed!!!");
}
}
for(i = 0; i < m; ++i){
char *path = paths[i];
image im = load_image_color(path,0,0);
image sized = letterbox_image(im, net->w, net->h);
//image sized = resize_image(im, net->w, net->h);
//image sized2 = resize_max(im, net->w);
//image sized = crop_image(sized2, -((net->w - sized2.w)/2), -((net->h - sized2.h)/2), net->w, net->h);
//resize_network(net, sized.w, sized.h);
layer l = net->layers[net->n-1];
float *X = sized.data;
time=what_time_is_it_now();
network_predict(net, X);
printf("Try Very Hard:");
printf("%s: Predicted in %f seconds.\n", path, what_time_is_it_now()-time);
int nboxes = 0;
detection *dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, 0, 1, &nboxes);
//printf("%d\n", nboxes);
//if (nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
if (nms) do_nms_sort(dets, nboxes, l.classes, nms);
draw_detections(im, dets, nboxes, thresh, names, alphabet, l.classes);
free_detections(dets, nboxes);
if(outfile){
save_image(im, outfile);
}
else{
char b[2048];
sprintf(b,"/home/ztj/tvm/darknet/data/multi/out/%s",GetFilename(path));//要改成自己的输出路径
save_image(im, b);
printf("save %s successfully!\n",GetFilename(path));
#ifdef OPENCV
cvNamedWindow("predictions", CV_WINDOW_NORMAL);
if(fullscreen){
cvSetWindowProperty("predictions", CV_WND_PROP_FULLSCREEN, CV_WINDOW_FULLSCREEN);
}
show_image(im, "predictions");
cvWaitKey(0);
cvDestroyAllWindows();
#endif
}
free_image(im);
free_image(sized);
if (filename) break;
}
}
}
}
第二步，在最前面添加*GetFilename(char *p)函数，注意strncpy(name,q,1);中的最后一个参数是图片文件名的长度，要根据实际情况更改。
#include "darknet.h"
#include <sys/stat.h>
#include <stdio.h>
#include <time.h>
#include <sys/types.h>
static int coco_ids[] = {1,2,3,4,5,6,7,8,9,10,11,13,14,15,16,17,18,19,20,21,22,23,24,25,27,28,31,32,33,34,35,36,37,38,39,40,41,42,43,44,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,67,70,72,73,74,75,76,77,78,79,80,81,82,84,85,86,87,88,89,90};
char *GetFilename(char *p)
{
static char name[20]={""};
char *q = strrchr(p,'/') + 1;
strncpy(name,q,1);//此处的1是图片文件名的长度，要根据实际情况更改。
return name;
}
第三步，在darknet目录下重新make。
第四步，将需要检测的图片路径写在一个txt文件中，例如：
/home/ztj/tvmtt/darknet/0.jpg
/home/ztj/tvmtt/darknet/1.jpg
/home/ztj/tvmtt/darknet/2.jpg
/home/ztj/tvmtt/darknet/3.jpg
/home/ztj/tvmtt/darknet/4.jpg
/home/ztj/tvmtt/darknet/5.jpg
/home/ztj/tvmtt/darknet/6.jpg
第五步，开始批量测试：
./darknet detector test cfg/voc.data cfg/yolov3.cfg yolov3.weights
程序提示输入图片的路径，我们在这里将第四步中的txt文件的路径填入，测试即开始。
第二部分 在TVM上YOLO-DarkNet多图测试
在TVM上部署YOLO-DarkNet的过程已经在之前的文章中介绍了。
要在TVM上进行多图测试，我们需要对之前的测试代码进行修改，主要修改是模型编译完成之后加入循环读入图片的过程，其中有一处路径需要修改成自己的图片输入路径（见注释），文件名以0.jpg 1.jpg这样的格式命名。测试代码如下：
# numpy and matplotlib
import numpy as np
import matplotlib.pyplot as plt
import sys
# tvm, relay
import tvm
from tvm import relay
from ctypes import *
from tvm.contrib.download import download_testdata
from tvm.relay.testing.darknet import __darknetffi__
import tvm.relay.testing.yolo_detection
import tvm.relay.testing.darknet
import datetime
# Model name
MODEL_NAME = 'yolov3'
CFG_NAME = MODEL_NAME + '.cfg'
WEIGHTS_NAME = MODEL_NAME + '.weights'
REPO_URL = 'https://github.com/dmlc/web-data/blob/master/darknet/'
CFG_URL = REPO_URL + 'cfg/' + CFG_NAME + '?raw=true'
WEIGHTS_URL = 'https://pjreddie.com/media/files/' + WEIGHTS_NAME
cfg_path = download_testdata(CFG_URL, CFG_NAME, module="darknet")
# cfg_path = "/home/ztj/.tvm_test_data/darknet/yolov3.cfg"
weights_path = download_testdata(WEIGHTS_URL, WEIGHTS_NAME, module="darknet")
# weights_path = "/home/ztj/.tvm_test_data/darknet/yolov3.weights"
# Download and Load darknet library
if sys.platform in ['linux', 'linux2']:
DARKNET_LIB = 'libdarknet2.0.so'
DARKNET_URL = REPO_URL + 'lib/' + DARKNET_LIB + '?raw=true'
elif sys.platform == 'darwin':
DARKNET_LIB = 'libdarknet_mac2.0.so'
DARKNET_URL = REPO_URL + 'lib_osx/' + DARKNET_LIB + '?raw=true'
else:
err = "Darknet lib is not supported on {} platform".format(sys.platform)
raise NotImplementedError(err)
lib_path = download_testdata(DARKNET_URL, DARKNET_LIB, module="darknet")
# lib_path = "/home/ztj/.tvm_test_data/darknet/libdarknet2.0.so"
# ******timepoint1-start*******
start1 = datetime.datetime.now()
# ******timepoint1-start*******
DARKNET_LIB = __darknetffi__.dlopen(lib_path)
net = DARKNET_LIB.load_network(cfg_path.encode('utf-8'), weights_path.encode('utf-8'), 0)
dtype = 'float32'
batch_size = 1
data = np.empty([batch_size, net.c, net.h, net.w], dtype)
shape_dict = {'data': data.shape}
print("Converting darknet to relay functions...")
mod, params = relay.frontend.from_darknet(net, dtype=dtype, shape=data.shape)
######################################################################
# Import the graph to Relay
# -------------------------
# compile the model
target = 'llvm'
target_host = 'llvm'
ctx = tvm.cpu(0)
data = np.empty([batch_size, net.c, net.h, net.w], dtype)
shape = {'data': data.shape}
print("Compiling the model...")
with relay.build_config(opt_level=3):
graph, lib, params = relay.build(mod,
target=target,
target_host=target_host,
params=params)
[neth, netw] = shape['data'][2:] # Current image shape is 608x608
# ******timepoint1-end*******
end1 = datetime.datetime.now()
# ******timepoint1-end*******
TEST_IMAGE_NUM = 7
coco_name = 'coco.names'
coco_url = REPO_URL + 'data/' + coco_name + '?raw=true'
font_name = 'arial.ttf'
font_url = REPO_URL + 'data/' + font_name + '?raw=true'
coco_path = download_testdata(coco_url, coco_name, module='data')
font_path = download_testdata(font_url, font_name, module='data')
# coco_path = "/home/ztj/.tvm_test_data/data/coco.names"
# font_path = "/home/ztj/.tvm_test_data/data/arial.ttf"
print(end1-start1)
for i in range(0,TEST_IMAGE_NUM):
# ******timepoint2-start*******
start2 = datetime.datetime.now()
# ******timepoint2-start*******
test_image = str(i) + '.jpg'
# print("Loading the test image...")
img_url = REPO_URL + 'data/' + test_image + '?raw=true'
# img_path = download_testdata(img_url, test_image, "data")
img_path = "/home/ztj/.tvm_test_data/data/darknet_multi/" + test_image //改成自己的图片路径
data = tvm.relay.testing.darknet.load_image(img_path, netw, neth)
from tvm.contrib import graph_runtime
m = graph_runtime.create(graph, lib, ctx)
# set inputs
m.set_input('data', tvm.nd.array(data.astype(dtype)))
m.set_input(**params)
# execute
# print("Running the test image...")
m.run()
# get outputs
tvm_out = []
if MODEL_NAME == 'yolov2':
layer_out = {}
layer_out['type'] = 'Region'
# Get the region layer attributes (n, out_c, out_h, out_w, classes, coords, background)
layer_attr = m.get_output(2).asnumpy()
layer_out['biases'] = m.get_output(1).asnumpy()
out_shape = (layer_attr[0], layer_attr[1]//layer_attr[0],
layer_attr[2], layer_attr[3])
layer_out['output'] = m.get_output(0).asnumpy().reshape(out_shape)
layer_out['classes'] = layer_attr[4]
layer_out['coords'] = layer_attr[5]
layer_out['background'] = layer_attr[6]
tvm_out.append(layer_out)
elif MODEL_NAME == 'yolov3':
for i in range(3):
layer_out = {}
layer_out['type'] = 'Yolo'
# Get the yolo layer attributes (n, out_c, out_h, out_w, classes, total)
layer_attr = m.get_output(i*4+3).asnumpy()
layer_out['biases'] = m.get_output(i*4+2).asnumpy()
layer_out['mask'] = m.get_output(i*4+1).asnumpy()
out_shape = (layer_attr[0], layer_attr[1]//layer_attr[0],
layer_attr[2], layer_attr[3])
layer_out['output'] = m.get_output(i*4).asnumpy().reshape(out_shape)
layer_out['classes'] = layer_attr[4]
tvm_out.append(layer_out)
# do the detection and bring up the bounding boxes
thresh = 0.5
nms_thresh = 0.45
img = tvm.relay.testing.darknet.load_image_color(img_path)
_, im_h, im_w = img.shape
dets = tvm.relay.testing.yolo_detection.fill_network_boxes((netw, neth), (im_w, im_h), thresh,
1, tvm_out)
last_layer = net.layers[net.n - 1]
tvm.relay.testing.yolo_detection.do_nms_sort(dets, last_layer.classes, nms_thresh)
with open(coco_path) as f:
content = f.readlines()
names = [x.strip() for x in content]
# print(names)
tvm.relay.testing.yolo_detection.draw_detections(font_path, img, dets, thresh, names, last_layer.classes)
# ******timepoint2-end*******
end2 = datetime.datetime.now()
# ******timepoint2-end*******
print(end2-start2)
# plt.imshow(img.transpose(1, 2, 0))
plt.imsave(test_image,img.transpose(1, 2, 0))
# plt.show()
第三部分 运行测试及性能对比
对直接运行及在TVM上运行分别进行十次重复测试，得到以下测试结果：