easy_vision.python.model.yolo

easy_vision.python.model.yolo.yolo

class easy_vision.python.model.yolo.yolo.YOLO(model_config, feature_dict, label_dict=None, mode='predict', categories=None)

Bases: easy_vision.python.model.detection_model.DetectionModel

__init__(model_config, feature_dict, label_dict=None, mode='predict', categories=None)

x.__init__(…) initializes x; see help(type(x)) for signature

build_loss_graph()

build_predict_graph()

classmethod create_class(name)

easy_vision.python.model.yolo.yolo_head

class easy_vision.python.model.yolo.yolo_head.YOLOHead(feature_dict, head_config, label_dict=None, mode='predict')

Bases: easy_vision.python.model.cv_head.CVHead

YOLOHead which helps to build multi-scale feature maps, placing different size of anchors on each feature map and calculate loc_loss and cls_loss

__init__(feature_dict, head_config, label_dict=None, mode='predict')

Parameters:

• feature_dict – must include two parts: 1. backbone output features 2. preprocessed batched image shape(preprocessed_input_shape)
• head_config – protos.yolo_pb2.YOLOHead
• mode – train/evaluate/predict

build_loss_graph()

build_postprocess_graph()

for post process of the head 1. box decode 2. box rescale 3. nms and clip boxes

build_predict_graph()

easy_vision.python.model.yolo.yolo_helper