efficientdet_d1(pretrained: bool = False, overrides: object = {})EfficientDet-D1 ().
Compound-scaled variant: EfficientNet-B1 backbone, BiFPN 88 channels with 4 repeats, head depth 3, 640x640 input. Approximately 6.6M parameters; COCO test-dev mAP of 39.6% (paper Table 2).
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently ignored.
**overridesobject= {}Keyword overrides forwarded into
EfficientDetConfig.Returns
EfficientDetForObjectDetectionDetector with the D1 configuration applied.
Notes
See Tan et al., 2020 (arXiv:1911.09070), Table 2.
Examples
>>> import lucid
>>> from lucid.models.vision.efficientdet import efficientdet_d1
>>> model = efficientdet_d1()
>>> x = lucid.randn(1, 3, 640, 640)
>>> out = model(x)
>>> out.pred_boxes.shape[-1]
4