def net_inference(model, reqs):
CTX.logger.info("inference begin...")
# datas = json.loads(args)
predictor = model['predictor']
classes_dict = model['labels']['class']
# threshold uses for default
threshold_dict = model['labels']['minMt'] # minModelThreshold
rets = []
nms = py_nms_wrapper(config.TEST.NMS)
box_voting = py_box_voting_wrapper(config.TEST.BOX_VOTING_IOU_THRESH, config.TEST.BOX_VOTING_SCORE_THRESH,
with_nms=True)
try:
for data in reqs:
try:
im = load_image(data['data']['uri'], body=data['data']['body'])
except ErrorBase as e:
rets.append({"code":e.code, "message": e.message, "result": None})
continue
# return [], 400, 'load image error'
if im.shape[0] > im.shape[1]:
long_side, short_side = im.shape[0], im.shape[1]
else:
long_side, short_side = im.shape[1], im.shape[0]
if short_side > 0 and float(long_side)/float(short_side) > 50.0:
msg = "aspect ration is too large, long_size:short_side should not larger than 50.0"
# raise ErrorBase.__init__(400, msg)
rets.append({"code": 400, "message": msg, "result": None})
continue
data_batch, data_names, im_scale = generate_batch(im)
scores, boxes, data_dict = im_detect(predictor,
data_batch,
data_names,
im_scale,
config)
det_ret = []
# labels.csv file not include background
for cls_index in sorted(classes_dict.keys()):
cls_ind = cls_index
cls_name = classes_dict.get(cls_ind)
cls_boxes = boxes[0][:, 4:8] if config.CLASS_AGNOSTIC else boxes[0][:, 4 * cls_ind:4 *4 * (cls_ind + 1)]
cls_scores = scores[0][:, cls_ind, np.newaxis]
threshold = float(threshold_dict[cls_ind])
keep = np.where(cls_scores > threshold)[0]
dets = np.hstack((cls_boxes, cls_scores)).astype(np.float32)[keep, :]
keep = nms(dets)
det_ret.extend(_build_result(det, cls_name, cls_ind, model['labels'])
for det in dets[keep, :])
# get review value
rets.append(dict(code=0,message='',result=dict(detections=det_ret)))
except Exception as e:
# print(traceback.format_exc())
CTX.logger.info("inference error:%s"%(traceback.format_exc()))
return [], 599, str(e)
return rets, 0, ''
def demo_net(cfg,predictor, dataset, image_set,
root_path, dataset_path, thresh, vis=False, use_box_voting=False,
test_file='test.txt',out_prefix='output',vis_image_dir='vis'):
"""
generate data_batch -> im_detect -> post process
:param predictor: Predictor
:param image_name: image name
:param vis: will save as a new image if not visualized
:return: None
"""
# visualization
nms = py_nms_wrapper(config.TEST.NMS)
box_voting = py_box_voting_wrapper(config.TEST.BOX_VOTING_IOU_THRESH, config.TEST.BOX_VOTING_SCORE_THRESH,
with_nms=True)
with open(test_file) as f:
image_set_index = [x.strip().split(' ')[0] for x in f.readlines()]
num_images = len(image_set_index)
num_classes = len(CLASSES)
all_boxes = [[[] for _ in xrange(num_images)]
for _ in xrange(num_classes)]
out_score_list,out_json_list = [],[]
jsonlistwithscore ,jsonlistwithoutscore = [[] for _ in xrange(num_images)],[[] for _ in xrange(num_images)]
predict_url(cfg, predictor, image_set_index, nms, box_voting, all_boxes, jsonlistwithscore,
jsonlistwithoutscore,
thresh, vis=False, use_box_voting=False, num_gpu=1)
fout = open(out_prefix + '_vali.txt','w')
fout_score = open(out_prefix + '_vali_score.txt', 'w')
for i in range(num_images):
fout.write(json.dumps(jsonlistwithoutscore[i]) + '\n')
fout.flush()
fout_score.write(json.dumps(jsonlistwithscore[i]) + '\n')
fout_score.flush()
print("num of images: detection:{}, gt:{}".format(len(all_boxes[0]), num_images))
#assert len(all_boxes) == num_images, 'calculations not complete'
# save results
cache_folder = os.path.join(root_path, 'cache')
if not os.path.exists(cache_folder):
os.mkdir(cache_folder)
cache_file = os.path.join(cache_folder, dataset + '_' + image_set + '_' + out_prefix + '_detections.pkl')
with open(cache_file, 'wb') as f:
cPickle.dump(all_boxes, f, cPickle.HIGHEST_PROTOCOL)
def demo_net(predictor,
dataset,
image_set,
root_path,
dataset_path,
thresh,
vis=False,
vis_image_dir='vis',
use_box_voting=False):
"""
generate data_batch -> im_detect -> post process
:param predictor: Predictor
:param image_name: image name
:param vis: will save as a new image if not visualized
:return: None
"""
# visualization
nms = py_nms_wrapper(config.TEST.NMS)
box_voting = py_box_voting_wrapper(config.TEST.BOX_VOTING_IOU_THRESH,
config.TEST.BOX_VOTING_SCORE_THRESH,
with_nms=True)
image_set_index_file = os.path.join(dataset_path, 'DET', 'ImageSets',
'DET', image_set + '.txt')
assert os.path.exists(
image_set_index_file), image_set_index_file + ' not found'
with open(image_set_index_file) as f:
image_set_index = [x.strip().split(' ')[0] for x in f.readlines()]
num_images = len(image_set_index)
num_classes = len(CLASSES)
all_boxes = [[[] for _ in xrange(num_images)] for _ in xrange(num_classes)]
i = 0
for index in image_set_index:
image_file = image_path_from_index(index, dataset_path, image_set)
print("processing {}/{} image:{}".format(i, num_images, image_file))
im = cv2.imread(image_file)
data_batch, data_names, im_scale = generate_batch(im)
scores, boxes, data_dict = im_detect(predictor, data_batch, data_names,
im_scale, config)
for cls in CLASSES:
cls_ind = CLASSES.index(cls)
#print cls_ind, 4 * cls_ind, 4 * (cls_ind + 1), boxes[0], boxes[0][:, 4 * cls_ind:4 * (cls_ind + 1)]
#cls_boxes = boxes[0][:, 4 * cls_ind:4 * (cls_ind + 1)]
cls_boxes = boxes[0][:, 4:8] if config.CLASS_AGNOSTIC else boxes[
0][:, 4 * cls_ind:4 * (cls_ind + 1)]
cls_scores = scores[0][:, cls_ind, np.newaxis]
keep = np.where(cls_scores >= thresh)[0]
cls_dets = np.hstack(
(cls_boxes, cls_scores)).astype(np.float32)[keep, :]
keep = nms(cls_dets)
# apply box voting after nms
if use_box_voting:
nms_cls_dets = cls_dets[keep, :]
all_boxes[cls_ind][i] = box_voting(nms_cls_dets, cls_dets)
else:
all_boxes[cls_ind][i] = cls_dets[keep, :]
boxes_this_image = [[]] + [
all_boxes[j][i] for j in xrange(1, len(CLASSES))
]
i += 1
if vis:
#vis_all_detection(data_dict['data'].asnumpy(), boxes_this_image, CLASSES, im_scale)
if not os.path.exists(vis_image_dir):
os.mkdir(vis_image_dir)
result_file = os.path.join(
vis_image_dir,
index.strip().split('/')[-1] + '_result' + '.JPEG')
print('results saved to %s' % result_file)
im = draw_all_detection(data_dict['data'].asnumpy(),
boxes_this_image, CLASSES, im_scale)
im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
cv2.imwrite(result_file, im)
print("num of images: detection:{}, gt:{}".format(len(all_boxes[0]),
num_images))
#assert len(all_boxes) == num_images, 'calculations not complete'
# save results
cache_folder = os.path.join(root_path, 'cache')
if not os.path.exists(cache_folder):
os.mkdir(cache_folder)
cache_file = os.path.join(cache_folder,
dataset + '_' + image_set + '_detections.pkl')
with open(cache_file, 'wb') as f:
cPickle.dump(all_boxes, f, cPickle.HIGHEST_PROTOCOL)
def net_inference(model):
"""
generate data_batch -> im_detect -> post process
:param predictor: Predictor
:param image_name: image name
:return: None
"""
# datas = json.loads(args)
predictor = model['predictor']
classes = model['classes']
threshold = model['threshold']
thresholds = model['thresholds']
rets = []
nms = py_nms_wrapper(config.TEST.NMS)
box_voting = py_box_voting_wrapper(config.TEST.BOX_VOTING_IOU_THRESH,
config.TEST.BOX_VOTING_SCORE_THRESH,
with_nms=True)
try:
time_str = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
fileOp = "/tmp/eval/init/20170930_guns_1083-begin-" + time_str + '.csv'
fileOp_op = open(fileOp, 'w')
time_str = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
fileOp_1 = "/tmp/eval/init/20170930_guns_1083-end-" + time_str + '.csv'
fileOp_1_op = open(fileOp_1, 'w')
fileOp_2 = "/tmp/eval/init/20170930_guns_1083-image-" + time_str + '.jpg'
for i in sorted(os.listdir("/tmp/eval/init/images")):
imageFile = os.path.join("/tmp/eval/init/images", i)
try:
im = load_image(imageFile, 50.0)
# cv2.imwrite('fileOp_2', im)
print(im[0, :])
# np.savetxt(fileOp_2, im, delimiter=",")
except ErrorBase as e:
rets.append({"code": e.code, "message": e.message})
continue
data_batch, data_names, im_scale = generate_batch(im)
print("*" * 100)
scores, boxes, data_dict = im_detect(predictor, data_batch,
data_names, im_scale, config)
det_ret = []
for cls_index, cls in enumerate(classes[1:], start=1):
if len(cls) > 1:
cls_ind = int(cls[0])
cls_name = cls[1]
else:
cls_ind = cls_index
cls_name = cls[0]
cls_boxes = boxes[0][:,
4:8] if config.CLASS_AGNOSTIC else boxes[
0][:, 4 * cls_ind:4 * (cls_ind + 1)]
cls_scores = scores[0][:, cls_ind, np.newaxis]
if len(classes) <= len(thresholds):
threshold = thresholds[cls_ind]
keep = np.where(cls_scores >= threshold)[0]
dets = np.hstack(
(cls_boxes, cls_scores)).astype(np.float32)[keep, :]
if "20170930_guns_1083.jpg" in imageFile:
# print(dets)
# print('*'*100)
# for i in dets:
# fileOp_op.write(i)
# fileOp_op.write('\n')
np.savetxt(fileOp, dets, delimiter=",")
pass
keep = nms(dets)
if "20170930_guns_1083.jpg" in imageFile:
# print("end"*10)
# print(dets[keep, :])
# print('*'*100)
# for i in dets:
# fileOp_1_op.write(i)
# fileOp_1_op.write('\n')
np.savetxt(fileOp_1, dets[keep, :], delimiter=",")
det_ret.extend(
_build_result(det, cls_name, cls_ind)
for det in dets[keep, :])
rets.append(
dict(code=0,
message=imageFile,
result=json.dumps(dict(detections=det_ret))))
except Exception, e:
print(traceback.format_exc())