def grid_result_eval(predict_path, log_path='grid_eval.log'):
pids4probes = np.genfromtxt(predict_path, delimiter=' ')
probe_shoot = [0, 0, 0, 0, 0]
for i, pids in enumerate(pids4probes):
for j, pid in enumerate(pids):
if pid - i == 775:
if j == 0:
for k in range(5):
probe_shoot[k] += 1
elif j < 5:
for k in range(1, 5):
probe_shoot[k] += 1
elif j < 10:
for k in range(2, 5):
probe_shoot[k] += 1
elif j < 20:
for k in range(3, 5):
probe_shoot[k] += 1
elif j < 50:
for k in range(4, 5):
probe_shoot[k] += 1
break
probe_acc = [shoot / len(pids4probes) for shoot in probe_shoot]
write(log_path, predict_path + '\n')
write(log_path,
'%.2f\t%.2f\t%.2f\n' % (probe_acc[0], probe_acc[1], probe_acc[2]))
print(predict_path)
print(probe_acc)
def result_eval(predict_path, log_path, TEST, QUERY):
res = np.genfromtxt(predict_path, delimiter=' ')
print('predict info get, extract gallery info start')
test_info = extract_info(TEST)
print('extract probe info start')
query_info = extract_info(QUERY)
print('start evaluate map and rank acc')
rank1, mAP = map_rank_quick_eval(query_info, test_info, res)
write(log_path, predict_path + '\n')
write(log_path, '%f\t%f\n' % (rank1, mAP))
def label_cattle_boxes():
img_pathes = read_lines('data/cattle.txt')
global cur_box_list
for img_name in img_pathes:
cur_box_list = []
global img, cur_img_path
cur_img_path = 'data/hard_cattle/' + img_name.strip()
img = cv2.imread(cur_img_path)
img = imutils.resize(img, width=400)
cv2.namedWindow('image')
cv2.setMouseCallback('image', on_mouse)
cv2.imshow('image', img)
cv2.waitKey(0)
for i in range(len(cur_box_list)):
cur_line = '%s\t%4f\t%4f\t%4f\t%4f\n' % (
cur_img_path, float(cur_box_list[i][0][0]) / img.shape[1],
float(cur_box_list[i][0][1]) / img.shape[0],
float(cur_box_list[i][1][0]) / img.shape[1],
float(cur_box_list[i][1][1]) / img.shape[0])
write('body_box.txt', cur_line)
def label_boxes(input_path, output_box_path):
img_pathes = read_lines(input_path)
global cur_box_list
for img_name in img_pathes:
cur_box_list = []
global img, cur_img_path
cur_img_path = img_name.strip()
img = cv2.imread(cur_img_path)
img = imutils.resize(img, width=400)
cv2.namedWindow('image')
cv2.setMouseCallback('image', on_mouse)
cv2.imshow('image', img)
cv2.waitKey(0)
for i in range(len(cur_box_list)):
cur_line = '%s\t%4f\t%4f\t%4f\t%4f\n' % (
cur_img_path, float(cur_box_list[i][0][0]) / img.shape[1],
float(cur_box_list[i][0][1]) / img.shape[0],
float(cur_box_list[i][1][0]) / img.shape[1],
float(cur_box_list[i][1][1]) / img.shape[0])
write(output_box_path, cur_line)
add_str_on_img(image, total_cnt)
image_np = load_image_into_numpy_array(image)
if num > 0:
# Visualization of the results of a detection.
result = vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
np.squeeze(valid_boxes).reshape(num, 4),
np.squeeze(valid_classes).astype(np.int32).reshape(num, ),
np.squeeze(valid_scores).reshape(num, ),
category_index,
use_normalized_coordinates=True,
min_score_thresh=score_thresh,
line_thickness=8)
Image.fromarray(result).save('detect4video/' +
image_path.split('/')[-1])
# total_cnt += num
else:
if num < 3:
write('no_target.txt', image_path + '\n')
image.save('detect4video/' + image_path.split('/')[-1])
# plt.figure(figsize=IMAGE_SIZE)
if num == 0:
print image_path
print total_cnt
os.system('mkdir detect4video2')
os.system('rm detect4video2/*')
for i, image_name in enumerate(sorted(os.listdir('detect4video'))):
shutil.copy('detect4video/' + image_name, 'detect4video2/%05d.jpg' % i)