easycv.models.detection.yolox_edge package¶
Submodules¶
easycv.models.detection.yolox_edge.yolox_edge module¶
- class easycv.models.detection.yolox_edge.yolox_edge.YOLOX_EDGE(stage: str = 'EDGE', model_type: str = 's', num_classes: int = 80, test_size: tuple = (640, 640), test_conf: float = 0.01, nms_thre: float = 0.65, pretrained: Optional[str] = None, depth: float = 1.0, width: float = 1.0, max_model_params: float = 0.0, max_model_flops: float = 0.0, activation: str = 'silu', in_channels: list = [256, 512, 1024], backbone=None, head=None)[source]¶
Bases:
easycv.models.detection.yolox.yolox.YOLOX
YOLOX model module. The module list is defined by create_yolov3_modules function. The network returns loss values from three YOLO layers during training and detection results during test.
- __init__(stage: str = 'EDGE', model_type: str = 's', num_classes: int = 80, test_size: tuple = (640, 640), test_conf: float = 0.01, nms_thre: float = 0.65, pretrained: Optional[str] = None, depth: float = 1.0, width: float = 1.0, max_model_params: float = 0.0, max_model_flops: float = 0.0, activation: str = 'silu', in_channels: list = [256, 512, 1024], backbone=None, head=None)[source]¶
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- training: bool¶