训练时的loss曲线，iou查看
在训练时保存log文件
./darknet detector train /home/wp/darknet/YOLOV3/cfg/myv3_det.data /home/wp/darknet/YOLOV3/cfg/my_yolov3.cfg >>train.log得到类似如下文件
Learning Rate: 0.001, Momentum: 0.9, Decay: 0.0005
Loaded: 0.561498 seconds
Region 82 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.390935, .5R: -nan, .75R: -nan, count: 0
Region 94 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.387395, .5R: -nan, .75R: -nan, count: 0
Region 106 Avg IOU: 0.098546, Class: 0.374210, Obj: 0.752171, No Obj: 0.531080, .5R: 0.125000, .75R: 0.000000, count: 8
Region 82 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.390945, .5R: -nan, .75R: -nan, count: 0
Region 94 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.387785, .5R: -nan, .75R: -nan, count: 0
Region 106 Avg IOU: 0.312301, Class: 0.452275, Obj: 0.686650, No Obj: 0.533953, .5R: 0.125000, .75R: 0.000000, count: 8
Region 82 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.400186, .5R: -nan, .75R: -nan, count: 0
Region 94 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.392681, .5R: -nan, .75R: -nan, count: 0
Region 106 Avg IOU: 0.145591, Class: 0.483727, Obj: 0.699570, No Obj: 0.531091, .5R: 0.125000, .75R: 0.000000, count: 8
Region 82 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.389850, .5R: -nan, .75R: -nan, count: 0
Region 94 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.388073, .5R: -nan, .75R: -nan, count: 0
Region 106 Avg IOU: 0.123178, Class: 0.344134, Obj: 0.561411, No Obj: 0.532049, .5R: 0.000000, .75R: 0.000000, count: 8
Region 82 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.387703, .5R: -nan, .75R: -nan, count: 0
Region 94 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.390149, .5R: -nan, .75R: -nan, count: 0
Region 106 Avg IOU: 0.078926, Class: 0.359554, Obj: 0.725995, No Obj: 0.528835, .5R: 0.125000, .75R: 0.000000, count: 8
Region 82 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.391989, .5R: -nan, .75R: -nan, count: 0
Region 94 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.388933, .5R: -nan, .75R: -nan, count: 0
Region 106 Avg IOU: 0.084757, Class: 0.466031, Obj: 0.659716, No Obj: 0.531660, .5R: 0.000000, .75R: 0.000000, count: 8
Region 82 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.396926, .5R: -nan, .75R: -nan, count: 0
Region 94 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.394189, .5R: -nan, .75R: -nan, count: 0
Region 106 Avg IOU: 0.083366, Class: 0.461135, Obj: 0.584269, No Obj: 0.530194, .5R: 0.000000, .75R: 0.000000, count: 8
Region 82 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.393838, .5R: -nan, .75R: -nan, count: 0
Region 94 Avg IOU: -nan, Class: -nan, Obj: -nan, No Obj: 0.391998, .5R: -nan, .75R: -nan, count: 0
Region 106 Avg IOU: 0.111406, Class: 0.378042, Obj: 0.661237, No Obj: 0.531444, .5R: 0.000000, .75R: 0.000000, count: 8
1: 2139.038574, 2139.038574 avg, 0.000000 rate, 7.929404 seconds, 64 imagesloss曲线
先执行如下脚本，需要改的参数为训练的log文件‘/media/wp/file/ubuntu/darknet/hello.txt’
import inspect
import os
import random
import sys
def extract_log(log_file, new_log_file, key_word):
with open(log_file, 'r') as f:
with open(new_log_file, 'w') as train_log:
# f = open(log_file)
# train_log = open(new_log_file, 'w')
for line in f:
# 去除多gpu的同步log
if 'Syncing' in line:
continue
# 去除除零错误的log
if 'nan' in line:
continue
if key_word in line:
train_log.write(line)
f.close()
train_log.close()
extract_log('/media/wp/file/ubuntu/darknet/hello.txt', 'train_log_loss.txt', 'images')
extract_log('/media/wp/file/ubuntu/darknet/hello.txt', 'train_log_iou.txt', 'IOU')再执行如下脚本生成训练时的loss曲线，该脚本会利用上一步生成的train_log_loss.txt文件
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
# %matplotlib inline
# lines =9873
lines = 25100
result = pd.read_csv('train_log_loss.txt', skiprows=[x for x in range(lines)], error_bad_lines=False,
names=['loss', 'avg', 'rate', 'seconds', 'images'])
result.head()
result['loss'] = result['loss'].str.split(' ').str.get(1)
result['avg'] = result['avg'].str.split(' ').str.get(1)
result['rate'] = result['rate'].str.split(' ').str.get(1)
result['seconds'] = result['seconds'].str.split(' ').str.get(1)
result['images'] = result['images'].str.split(' ').str.get(1)
result.head()
result.tail()
# print(result.head())
# print(result.tail())import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
# %matplotlib inline
lines = 9873
result = pd.read_csv('train_log_loss.txt', skiprows=[x for x in range(lines) if ((x < 1000))], error_bad_lines=False,
names=['loss', 'avg', 'rate', 'seconds', 'images'])
result.head()
result['loss'] = result['loss'].str.split(' ').str.get(1)
result['avg'] = result['avg'].str.split(' ').str.get(1)
result['rate'] = result['rate'].str.split(' ').str.get(1)
result['seconds'] = result['seconds'].str.split(' ').str.get(1)
result['images'] = result['images'].str.split(' ').str.get(1)
result.head()
result.tail()
# print(result.head())
# print(result.tail())
# print(result.dtypes)
print(result['loss'])
print(result['avg'])
print(result['rate'])
print(result['seconds'])
print(result['images'])
result['loss'] = pd.to_numeric(result['loss'])
result['avg'] = pd.to_numeric(result['avg'])
result['rate'] = pd.to_numeric(result['rate'])
result['seconds'] = pd.to_numeric(result['seconds'])
result['images'] = pd.to_numeric(result['images'])
result.dtypes
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
ax.plot(result['avg'].values, label='avg_loss')
# ax.plot(result['loss'].values,label='loss')
ax.legend(loc='best')
ax.set_title('The loss curves')
ax.set_xlabel('batches')
fig.savefig('avg_loss')
# fig.savefig('loss')
# print(result.dtypes)
print(result['loss'])
print(result['avg'])
print(result['rate'])
print(result['seconds'])
print(result['images'])
result['loss'] = pd.to_numeric(result['loss'])
result['avg'] = pd.to_numeric(result['avg'])
result['rate'] = pd.to_numeric(result['rate'])
result['seconds'] = pd.to_numeric(result['seconds'])
result['images'] = pd.to_numeric(result['images'])
result.dtypes
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
ax.plot(result['avg'].values, label='avg_loss')
# ax.plot(result['loss'].values,label='loss')
ax.legend(loc='best')
ax.set_title('The loss curves')
ax.set_xlabel('batches')
fig.savefig('avg_loss')
# fig.savefig('loss')iou曲线
执行如下脚本可以生成iou变化曲线，该脚本会利用train_log_iou.txt文件
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
# %matplotlib inline
lines = 1994726
result = pd.read_csv('train_log_iou.txt', skiprows=[x for x in range(lines) if (x % 39 != 0 | (x < 1000))],
error_bad_lines=False, names=['Region Avg IOU', 'Class', 'Obj', 'No Obj', 'Avg Recall', 'count'])
result.head()
result['Region Avg IOU'] = result['Region Avg IOU'].str.split(': ').str.get(1)
result['Class'] = result['Class'].str.split(': ').str.get(1)
result['Obj'] = result['Obj'].str.split(': ').str.get(1)
result['No Obj'] = result['No Obj'].str.split(': ').str.get(1)
result['Avg Recall'] = result['Avg Recall'].str.split(': ').str.get(1)
result['count'] = result['count'].str.split(': ').str.get(1)
result.head()
result.tail()
# print(result.head())
# print(result.tail())
# print(result.dtypes)
print(result['Region Avg IOU'])
result['Region Avg IOU'] = pd.to_numeric(result['Region Avg IOU'])
result['Class'] = pd.to_numeric(result['Class'])
result['Obj'] = pd.to_numeric(result['Obj'])
result['No Obj'] = pd.to_numeric(result['No Obj'])
result['Avg Recall'] = pd.to_numeric(result['Avg Recall'])
result['count'] = pd.to_numeric(result['count'])
result.dtypes
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
ax.plot(result['Region Avg IOU'].values, label='Region Avg IOU')
# ax.plot(result['Class'].values,label='Class')
# ax.plot(result['Obj'].values,label='Obj')
# ax.plot(result['No Obj'].values,label='No Obj')
# ax.plot(result['Avg Recall'].values,label='Avg Recall')
# ax.plot(result['count'].values,label='count')
ax.legend(loc='best')
# ax.set_title('The Region Avg IOU curves')
ax.set_title('The Region Avg IOU curves')
ax.set_xlabel('batches')
# fig.savefig('Avg IOU')
fig.savefig('Region Avg IOU')
测试集的recall，map计算
recall计算
首先要把制作数据集时的测试集中的txt文件修改，把data/coco_val_5k.list改成自己的路径，如下所示
//list *plist = get_paths("data/coco_val_5k.list");
list *plist = get_paths("valid-tiny-yolo.txt");
#重新编译
make -j8
#执行recall 函数
./darknet detector recall cfg/voc.data cfg/tiny-yolo.cfg backup/tiny-yolo-voc_final.weights得到如下结果
0 0 1 RPs/Img: 1.00 IOU: 8.40% Recall:0.00%
1 1 2 RPs/Img: 2.00 IOU: 42.10% Recall:50.00%
2 1 3 RPs/Img: 2.00 IOU: 30.51% Recall:33.33%
3 1 4 RPs/Img: 2.50 IOU: 25.33% Recall:25.00%
4 2 5 RPs/Img: 2.40 IOU: 33.25% Recall:40.00%
格式如下
Number Correct Total Rps/Img IOU Recall map计算
使用voc的map计算方式，首先通过valid命令，遍历一遍测试数据集，跑出来训练好的网络在这个测试数据集的结果，命令如下
darknet detector valid cfg/voc.data cfg/tiny_yolo_voc.cfg tiny_yolo_voc.weights
注意：在执行该命令的时候，需要你的当前路径下有一个results的文件夹，不然会报segmentation fault的错误。
会在result文件夹生成comp4_det_test_fish.txt之类的文件
创建和voc格式的数据集
VOCdevkit2007
|__VOC2007
|__Annotations 把所有的xml放入该文件夹
|__ImageSets
|__Main
|__test.txt 该文件的每一行为一张图片的名字，不包括后缀，比如直接为test1000000
|__annotations_cache
计算map要用到两个脚本voc_eval.py和reval_voc.py，把两个脚本放到darknet的根目录
reval_voc.py
#!/usr/bin/env python
# Adapt from ->
# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
# <- Written by Yaping Sun
"""Reval = re-eval. Re-evaluate saved detections."""
import os, sys, argparse
import numpy as np
import cPickle
from voc_eval import voc_eval
def parse_args():
"""
Parse input arguments
"""
parser = argparse.ArgumentParser(description='Re-evaluate results')
parser.add_argument('output_dir', nargs=1, help='results directory',
type=str)
parser.add_argument('--voc_dir', dest='voc_dir', default='data/VOCdevkit', type=str)
parser.add_argument('--year', dest='year', default='2017', type=str)
parser.add_argument('--image_set', dest='image_set', default='test', type=str)
parser.add_argument('--classes', dest='class_file', default='data/voc.names', type=str)
if len(sys.argv) == 1:
parser.print_help()
sys.exit(1)
args = parser.parse_args()
return args
def get_voc_results_file_template(image_set, out_dir = 'results'):
filename = 'comp4_det_' + image_set + '_{:s}.txt'
path = os.path.join(out_dir, filename)
return path
def do_python_eval(devkit_path, year, image_set, classes, output_dir = 'results'):
annopath = os.path.join(
devkit_path,
'VOC' + year,
'Annotations',
'{:s}.xml')
imagesetfile = os.path.join(
devkit_path,
'VOC' + year,
'ImageSets',
'Main',
image_set + '.txt')
cachedir = os.path.join(devkit_path, 'annotations_cache')
aps = []
# The PASCAL VOC metric changed in 2010
use_07_metric = True if int(year) < 2010 else False
print 'VOC07 metric? ' + ('Yes' if use_07_metric else 'No')
if not os.path.isdir(output_dir):
os.mkdir(output_dir)
for i, cls in enumerate(classes):
if cls == '__background__':
continue
filename = get_voc_results_file_template(image_set).format(cls)
rec, prec, ap = voc_eval(
filename, annopath, imagesetfile, cls, cachedir, ovthresh=0.5,
use_07_metric=use_07_metric)
aps += [ap]
print('AP for {} = {:.4f}'.format(cls, ap))
with open(os.path.join(output_dir, cls + '_pr.pkl'), 'w') as f:
cPickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f)
print('Mean AP = {:.4f}'.format(np.mean(aps)))
print('~~~~~~~~')
print('Results:')
for ap in aps:
print('{:.3f}'.format(ap))
print('{:.3f}'.format(np.mean(aps)))
print('~~~~~~~~')
print('')
print('--------------------------------------------------------------')
print('Results computed with the **unofficial** Python eval code.')
print('Results should be very close to the official MATLAB eval code.')
print('-- Thanks, The Management')
print('--------------------------------------------------------------')
if __name__ == '__main__':
args = parse_args()
output_dir = os.path.abspath(args.output_dir[0])
with open(args.class_file, 'r') as f:
lines = f.readlines()
classes = [t.strip('\n') for t in lines]
print 'Evaluating detections'
do_python_eval(args.voc_dir, args.year, args.image_set, classes, output_dir)
voc_eval.py
# --------------------------------------------------------
# Fast/er R-CNN
# Licensed under The MIT License [see LICENSE for details]
# Written by Bharath Hariharan
# --------------------------------------------------------
import xml.etree.ElementTree as ET
import os
import cPickle
import numpy as np
def parse_rec(filename):
""" Parse a PASCAL VOC xml file """
tree = ET.parse(filename)
objects = []
for obj in tree.findall('object'):
obj_struct = {}
obj_struct['name'] = obj.find('name').text
#obj_struct['pose'] = obj.find('pose').text
#obj_struct['truncated'] = int(obj.find('truncated').text)
obj_struct['difficult'] = int(obj.find('difficult').text)
bbox = obj.find('bndbox')
obj_struct['bbox'] = [int(bbox.find('xmin').text),
int(bbox.find('ymin').text),
int(bbox.find('xmax').text),
int(bbox.find('ymax').text)]
objects.append(obj_struct)
return objects
def voc_ap(rec, prec, use_07_metric=False):
""" ap = voc_ap(rec, prec, [use_07_metric])
Compute VOC AP given precision and recall.
If use_07_metric is true, uses the
VOC 07 11 point method (default:False).
"""
if use_07_metric:
# 11 point metric
ap = 0.
for t in np.arange(0., 1.1, 0.1):
if np.sum(rec >= t) == 0:
p = 0
else:
p = np.max(prec[rec >= t])
ap = ap + p / 11.
else:
# correct AP calculation
# first append sentinel values at the end
mrec = np.concatenate(([0.], rec, [1.]))
mpre = np.concatenate(([0.], prec, [0.]))
# compute the precision envelope
for i in range(mpre.size - 1, 0, -1):
mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])
# to calculate area under PR curve, look for points
# where X axis (recall) changes value
i = np.where(mrec[1:] != mrec[:-1])[0]
# and sum (\Delta recall) * prec
ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])
return ap
def voc_eval(detpath,
annopath,
imagesetfile,
classname,
cachedir,
ovthresh=0.5,
use_07_metric=False):
"""rec, prec, ap = voc_eval(detpath,
annopath,
imagesetfile,
classname,
[ovthresh],
[use_07_metric])
Top level function that does the PASCAL VOC evaluation.
detpath: Path to detections
detpath.format(classname) should produce the detection results file.
annopath: Path to annotations
annopath.format(imagename) should be the xml annotations file.
imagesetfile: Text file containing the list of images, one image per line.
classname: Category name (duh)
cachedir: Directory for caching the annotations
[ovthresh]: Overlap threshold (default = 0.5)
[use_07_metric]: Whether to use VOC07's 11 point AP computation
(default False)
"""
# assumes detections are in detpath.format(classname)
# assumes annotations are in annopath.format(imagename)
# assumes imagesetfile is a text file with each line an image name
# cachedir caches the annotations in a pickle file
# first load gt
if not os.path.isdir(cachedir):
os.mkdir(cachedir)
cachefile = os.path.join(cachedir, 'annots.pkl')
# read list of images
with open(imagesetfile, 'r') as f:
lines = f.readlines()
imagenames = [x.strip() for x in lines]
if not os.path.isfile(cachefile):
# load annots
recs = {}
for i, imagename in enumerate(imagenames):
recs[imagename] = parse_rec(annopath.format(imagename))
if i % 100 == 0:
print 'Reading annotation for {:d}/{:d}'.format(
i + 1, len(imagenames))
# save
print 'Saving cached annotations to {:s}'.format(cachefile)
with open(cachefile, 'w') as f:
cPickle.dump(recs, f)
else:
# load
with open(cachefile, 'r') as f:
recs = cPickle.load(f)
# extract gt objects for this class
class_recs = {}
npos = 0
for imagename in imagenames:
R = [obj for obj in recs[imagename] if obj['name'] == classname]
bbox = np.array([x['bbox'] for x in R])
difficult = np.array([x['difficult'] for x in R]).astype(np.bool)
det = [False] * len(R)
npos = npos + sum(~difficult)
class_recs[imagename] = {'bbox': bbox,
'difficult': difficult,
'det': det}
# read dets
detfile = detpath.format(classname)
with open(detfile, 'r') as f:
lines = f.readlines()
splitlines = [x.strip().split(' ') for x in lines]
image_ids = [x[0] for x in splitlines]
confidence = np.array([float(x[1]) for x in splitlines])
BB = np.array([[float(z) for z in x[2:]] for x in splitlines])
# sort by confidence
sorted_ind = np.argsort(-confidence)
sorted_scores = np.sort(-confidence)
BB = BB[sorted_ind, :]
image_ids = [image_ids[x] for x in sorted_ind]
# go down dets and mark TPs and FPs
nd = len(image_ids)
tp = np.zeros(nd)
fp = np.zeros(nd)
for d in range(nd):
R = class_recs[image_ids[d]]
bb = BB[d, :].astype(float)
ovmax = -np.inf
BBGT = R['bbox'].astype(float)
if BBGT.size > 0:
# compute overlaps
# intersection
ixmin = np.maximum(BBGT[:, 0], bb[0])
iymin = np.maximum(BBGT[:, 1], bb[1])
ixmax = np.minimum(BBGT[:, 2], bb[2])
iymax = np.minimum(BBGT[:, 3], bb[3])
iw = np.maximum(ixmax - ixmin + 1., 0.)
ih = np.maximum(iymax - iymin + 1., 0.)
inters = iw * ih
# union
uni = ((bb[2] - bb[0] + 1.) * (bb[3] - bb[1] + 1.) +
(BBGT[:, 2] - BBGT[:, 0] + 1.) *
(BBGT[:, 3] - BBGT[:, 1] + 1.) - inters)
overlaps = inters / uni
ovmax = np.max(overlaps)
jmax = np.argmax(overlaps)
if ovmax > ovthresh:
if not R['difficult'][jmax]:
if not R['det'][jmax]:
tp[d] = 1.
R['det'][jmax] = 1
else:
fp[d] = 1.
else:
fp[d] = 1.
# compute precision recall
fp = np.cumsum(fp)
tp = np.cumsum(tp)
rec = tp / float(npos)
# avoid divide by zero in case the first detection matches a difficult
# ground truth
prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)
ap = voc_ap(rec, prec, use_07_metric)
return rec, prec, ap然后执行
python reval_voc.py --voc_dir VOCdevkit2007 --year 2007 --image_set test --class ./data/voc.names .
VOCdevkit2007刚才建的数据集根目录的路径
./data/voc.names为类别文件，格式为每行一个类别结果如下所示
Evaluating detections
VOC07 metric? Yes
Reading annotation for 1/279
Reading annotation for 101/279
Reading annotation for 201/279
Saving cached annotations to /media/wp/file/ubuntu/darknet/results/VOCdevkit2007/annotations_cache/annots.pkl
AP for uav = 0.9042
Mean AP = 0.9042
~~~~~~~~
Results:
0.904
0.904
~~~~~~~~
--------------------------------------------------------------
Results computed with the **unofficial** Python eval code.
Results should be very close to the official MATLAB eval code.
-- Thanks, The Management
--------------------------------------------------------------
Process finished with exit code 0如果遇到问题，一般就是路径问题，可以在pycharm下debug，看什么地方路径出错了
扫一扫
247
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
