efficientdet_d6(pretrained: bool = False, overrides: object = {})EfficientDet-D6 ().
Compound-scaled variant: EfficientNet-B6 backbone, BiFPN 384 channels with 8 repeats, head depth 5, 1280x1280 input. Approximately 51.9M parameters; COCO test-dev mAP of 51.7% (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 D6 configuration applied.
Notes
See Tan et al., 2020 (arXiv:1911.09070), Table 2.
Examples
>>> import lucid
>>> from lucid.models.vision.efficientdet import efficientdet_d6
>>> model = efficientdet_d6()
>>> x = lucid.randn(1, 3, 1280, 1280)
>>> out = model(x)
>>> out.pred_boxes.shape[-1]
4