MCPcopy Create free account
hub / github.com/HobbitLong/PyContrast / resnext152_32x8d

Function resnext152_32x8d

pycontrast/networks/resnet.py:355–365  ·  view source on GitHub ↗

r"""ResNeXt-152 32x8d 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 download

(pretrained=False, progress=True, **kwargs)

Source from the content-addressed store, hash-verified

353
354
355def resnext152_32x8d(pretrained=False, progress=True, **kwargs):
356 r"""ResNeXt-152 32x8d model from
357 `"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.pdf>`_
358 Args:
359 pretrained (bool): If True, returns a model pre-trained on ImageNet
360 progress (bool): If True, displays a progress bar of the download to stderr
361 """
362 kwargs['groups'] = 32
363 kwargs['width_per_group'] = 8
364 return _resnet('resnext152_32x8d', Bottleneck, [3, 8, 36, 3],
365 pretrained, progress, **kwargs)
366
367
368def resnext152_64x4d(pretrained=False, progress=True, **kwargs):

Callers

nothing calls this directly

Calls 1

_resnetFunction · 0.85

Tested by

no test coverage detected