efficientdet_d4(pretrained: bool = False, overrides: object = {})EfficientDet-D4 ().
Compound-scaled variant: EfficientNet-B4 backbone, BiFPN 224 channels with 7 repeats, head depth 4, 1024x1024 input. Approximately 20.7M parameters; COCO test-dev mAP of 49.4% (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 D4 configuration applied.
Notes
See Tan et al., 2020 (arXiv:1911.09070), Table 2.
Examples
>>> import lucid
>>> from lucid.models.vision.efficientdet import efficientdet_d4
>>> model = efficientdet_d4()
>>> x = lucid.randn(1, 3, 1024, 1024)
>>> out = model(x)
>>> out.pred_boxes.shape[-1]
4