MCPcopy Create free account
hub / github.com/AtlasAnalyticsLab/AdaFisher / wide_resnet50_2

Function wide_resnet50_2

Image_Classification/src/models/resnet.py:305–315  ·  view source on GitHub ↗

r"""Wide ResNet-50-2 model from `"Wide Residual Networks" `_ The model is the same as ResNet except for the bottleneck number of channels which is twice larger in every block. The number of channels in outer 1x1 convolutions is the same, e.g. la

(**kwargs)

Source from the content-addressed store, hash-verified

303
304
305def wide_resnet50_2(**kwargs):
306 r"""Wide ResNet-50-2 model from
307 `"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
308
309 The model is the same as ResNet except for the bottleneck number of channels
310 which is twice larger in every block. The number of channels in outer 1x1
311 convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
312 channels, and in Wide ResNet-50-2 has 2048-1024-2048.
313 """
314 kwargs['width_per_group'] = 64 * 2
315 return _resnet('wide_resnet50_2', Bottleneck, [3, 4, 6, 3], **kwargs)
316
317
318def wide_resnet101_2(**kwargs):

Callers

nothing calls this directly

Calls 1

_resnetFunction · 0.85

Tested by

no test coverage detected