import torch
import numpy as np
import pickle
import sys
import os
if sys.version_info[0] == 2:
import xml.etree.cElementTree as ET
else:
import xml.etree.ElementTree as ET
sys.path.append('./RefineDet.PyTorch')
from data import VOC_CLASSES as labelmap
import argparse
parser = argparse.ArgumentParser(
description='Single Shot MultiBox Detector Evaluation')
parser.add_argument('--datasets_path',
default='./RefineDet.PyTorch/data/VOCdevkit/', type=str,)
parser.add_argument('--result_path',
default=None, type=str,)
args = parser.parse_args()
voc_root = args.datasets_path
result_path = args.result_path
annopath = os.path.join(voc_root, 'VOC2007', 'Annotations', '%s.xml')
imgpath = os.path.join(voc_root, 'VOC2007', 'JPEGImages', '%s.jpg')
imgsetpath = os.path.join(voc_root, 'VOC2007', 'ImageSets',
'Main', '{:s}.txt')
YEAR = '2007'
devkit_path = voc_root + 'VOC' + YEAR
dataset_mean = (104, 117, 123)
set_type = 'test'
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) - 1,
int(bbox.find('ymin').text) - 1,
int(bbox.find('xmax').text) - 1,
int(bbox.find('ymax').text) - 1]
objects.append(obj_struct)
return objects
def get_output_dir(name, phase):
"""Return the directory where experimental artifacts are placed.
If the directory does not exist, it is created.
A canonical path is built using the name from an imdb and a network
(if not None).
"""
filedir = os.path.join(name, phase)
if not os.path.exists(filedir):
os.makedirs(filedir)
return filedir
def get_voc_results_file_template(image_set, cls):
filename = 'det_' + image_set + '_%s.txt' % (cls)
filedir = os.path.join(devkit_path, 'results')
if not os.path.exists(filedir):
os.makedirs(filedir)
path = os.path.join(filedir, filename)
return path
def write_voc_results_file(all_boxes, dataset):
for cls_ind, cls in enumerate(labelmap):
print('Writing {:s} VOC results file'.format(cls))
filename = get_voc_results_file_template(set_type, cls)
with open(filename, 'wt') as f:
for im_ind, index in enumerate(dataset):
dets = all_boxes[cls_ind+1][im_ind]
if dets == []:
continue
for k in range(dets.shape[0]):
f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'.
format(index[1], dets[k, -1],
dets[k, 0] + 1, dets[k, 1] + 1,
dets[k, 2] + 1, dets[k, 3] + 1))
def do_python_eval(output_dir='output', use_07=True):
cachedir = os.path.join(devkit_path, 'annotations_cache')
aps = []
use_07_metric = use_07
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(labelmap):
filename = get_voc_results_file_template(set_type, cls)
rec, prec, ap = voc_eval(
filename, annopath, imgsetpath.format(set_type), 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'), 'wb') as f:
pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f)
print('Mean AP = {:.4f}'.format(np.mean(aps)))
print('~~~~~~~~')
print('Results:')
for ap in aps:
print('{:.4f}'.format(ap))
print('{:.4f}'.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('--------------------------------------------------------------')
def voc_ap(rec, prec, use_07_metric=True):
""" 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:True).
"""
if use_07_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:
mrec = np.concatenate(([0.], rec, [1.]))
mpre = np.concatenate(([0.], prec, [0.]))
for i in range(mpre.size - 1, 0, -1):
mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])
i = np.where(mrec[1:] != mrec[:-1])[0]
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=True):
"""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 True)
"""
if not os.path.isdir(cachedir):
os.mkdir(cachedir)
cachefile = os.path.join(cachedir, 'annots.pkl')
with open(imagesetfile, 'r') as f:
lines = f.readlines()
imagenames = [x.strip() for x in lines]
if not os.path.isfile(cachefile):
recs = {}
for i, imagename in enumerate(imagenames):
recs[imagename] = parse_rec(annopath % (imagename))
if i % 100 == 0:
print('Reading annotation for {:d}/{:d}'.format(
i + 1, len(imagenames)))
print('Saving cached annotations to {:s}'.format(cachefile))
with open(cachefile, 'wb') as f:
pickle.dump(recs, f)
else:
with open(cachefile, 'rb') as f:
recs = pickle.load(f)
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}
detfile = detpath.format(classname)
with open(detfile, 'r') as f:
lines = f.readlines()
if any(lines) == 1:
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])
sorted_ind = np.argsort(-confidence)
sorted_scores = np.sort(-confidence)
BB = BB[sorted_ind, :]
image_ids = [image_ids[x] for x in sorted_ind]
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:
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, 0.)
ih = np.maximum(iymax - iymin, 0.)
inters = iw * ih
uni = ((bb[2] - bb[0]) * (bb[3] - bb[1]) +
(BBGT[:, 2] - BBGT[:, 0]) *
(BBGT[:, 3] - BBGT[:, 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.
fp = np.cumsum(fp)
tp = np.cumsum(tp)
rec = tp / float(npos)
prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)
ap = voc_ap(rec, prec, use_07_metric)
else:
rec = -1.
prec = -1.
ap = -1.
return rec, prec, ap
def evaluate_detections(box_list, output_dir, dataset):
write_voc_results_file(box_list, dataset)
do_python_eval(output_dir)