def __init__(self, app_name, cfg):
super(InferenceServer, self).__init__(app_name)
self.inference_req = InferenceReq()
self.classes = aisdk.common.other.make_synset(
cfg['model_files']['labels.csv'])
label_file = cfg['model_files']['labels.csv']
self.labels = parse_label_file(label_file)
yaml_file = os.path.join(os.path.abspath(os.path.dirname(__file__)),
'resnet.yaml')
update_config(yaml_file)
def __init__(self, app_name, cfg):
super(InferenceServer, self).__init__(app_name)
self.inference_req = InferenceReq()
percent_fine = float(cfg['custom_params']['percentage_fine'])
fine_labels = str(cfg['model_files']["fine_labels.csv"])
dict_label = parse_label_file(fine_labels)
det_labelfile = str(cfg['model_files']["det_labels.csv"])
det_label_dict = parse_label_file(det_labelfile)
self.cls_model = {
"percentage_fine": percent_fine,
"dict_label": dict_label,
}
self.det_model = {'label': det_label_dict}
self.det_label_dict = det_label_dict
class InferenceServer(BaseInferenceServer):
def __init__(self, app_name, cfg):
super(InferenceServer, self).__init__(app_name)
self.inference_req = InferenceReq()
percent_fine = float(cfg['custom_params']['percentage_fine'])
percent_coarse = float(cfg['custom_params']['percentage_coarse'])
fine_labels = str(cfg['model_files']["fine_labels.csv"])
dict_label = parse_label_file(fine_labels)
coarse_labels = str(cfg['model_files']['coarse_labels.csv'])
label_map_dict = get_label_map(coarse_labels)
det_labelfile = str(cfg['model_files']["det_labels.csv"])
det_label_dict = parse_label_file(det_labelfile)
self.cls_model = {
"percentage_fine": percent_fine,
"percentage_coarse": percent_coarse,
"dict_label": dict_label,
"label_map_dict": label_map_dict
}
self.det_model = {'label': det_label_dict}
self.det_label_dict = det_label_dict
def net_inference(self, request):
assert isinstance(request, pb.InferenceRequest)
img = load_imagev2(request.data.body)
assert img.ndim == 3 # TODO
img_height, img_width, _ = img.shape
img_cls = cls_preProcessImage(img)
img_det = det_preProcessImage(img)
forward_req = {'img_cls': img_cls, 'img_det': img_det}
msg = pb.ForwardMsg(network_input_buf=cPickle.dumps(
forward_req, protocol=cPickle.HIGHEST_PROTOCOL),
reqid=request.reqid)
msg_out = self.inference_req.inference_msg(msg)
output = cPickle.loads(msg_out.network_output_buf)
image_index = json.loads(
msg_out.meta['data'].decode('utf8'))['image_index']
cls_result = cls_post_eval(output['output_fine'],
output['output_coarse'], image_index,
self.cls_model)
det_result = det_post_eval(img_height, img_width, output['output_det'],
self.det_label_dict, image_index)
cls_result = cls_merge_det(cls_result, det_result, self.cls_model,
self.det_model)
cls_result = merge_confidences(cls_result, self.cls_model)
resp = postProcess(cls_result, det_result, self.det_model)
return pb.InferenceResponse(code=200, result=json.dumps(resp))
def __init__(self, app_name, cfg):
super(InferenceServer, self).__init__(app_name)
net = aisdk.common.mxnet_base.net
conf = net.NetConfig()
conf.parse(cfg)
label_file = conf.file_synset
inference_req = InferenceReq()
self.net = net
self.labels = net.load_labels(label_file)
self.image_width = conf.image_width
self.image_height = conf.image_height
self.mean_value = conf.value_mean
self.std_value = conf.value_std
self.inference_req = inference_req
class InferenceServer(BaseInferenceServer):
def __init__(self, app_name, cfg):
super(InferenceServer, self).__init__(app_name)
self.inference_req = InferenceReq()
self.classes = aisdk.common.other.make_synset(
cfg['model_files']['labels.csv'])
label_file = cfg['model_files']['labels.csv']
self.labels = parse_label_file(label_file)
yaml_file = os.path.join(os.path.abspath(os.path.dirname(__file__)),
'resnet.yaml')
update_config(yaml_file)
def net_inference(self, request):
classes_dict = self.labels['class']
threshold_dict = self.labels['minMt'] # minModelThreshold
assert isinstance(request, pb.InferenceRequest)
img = load_imagev2(request.data.body)
assert img.ndim == 3 # TODO
nms = py_nms_wrapper(config.TEST.NMS)
if img.shape[0] > img.shape[1]:
long_side, short_side = img.shape[0], img.shape[1]
else:
long_side, short_side = img.shape[1], img.shape[0]
if short_side > 0 and float(long_side) / float(short_side) > 50.0:
raise ErrorBase(
400,
'aspect ration is too large, long_size:short_side should not larger than 50.0'
)
batch = generate_batch(img)
msg = pb.ForwardMsg()
msg.network_input_buf = cPickle.dumps(
batch, protocol=cPickle.HIGHEST_PROTOCOL)
msg_out = self.inference_req.inference_msg(msg)
scores = []
boxes = []
r = cPickle.loads(msg_out.network_output_buf)
scores.append(r['scores'])
boxes.append(r['boxes'])
det_ret = []
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, self.labels)
for det in dets[keep, :])
return pb.InferenceResponse(code=200,
result=json.dumps({'detections': det_ret}))