MCPcopy Create free account
hub / github.com/OpenDriveLab/TCP / resnext50_32x4d

Function resnext50_32x4d

TCP/resnet.py:328–339  ·  view source on GitHub ↗

r"""ResNeXt-50 32x4d model from `"Aggregated Residual Transformation for Deep Neural Networks" `_. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If True, displays a progress bar of the downloa

(pretrained: bool = False, progress: bool = True, **kwargs: Any)

Source from the content-addressed store, hash-verified

326
327
328def resnext50_32x4d(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
329 r"""ResNeXt-50 32x4d model from
330 `"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.pdf>`_.
331
332 Args:
333 pretrained (bool): If True, returns a model pre-trained on ImageNet
334 progress (bool): If True, displays a progress bar of the download to stderr
335 """
336 kwargs['groups'] = 32
337 kwargs['width_per_group'] = 4
338 return _resnet('resnext50_32x4d', Bottleneck, [3, 4, 6, 3],
339 pretrained, progress, **kwargs)
340
341
342def resnext101_32x8d(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:

Callers

nothing calls this directly

Calls 1

_resnetFunction · 0.85

Tested by

no test coverage detected