cutcutcodec.core.analysis.video.quality.uvq_google.custom_nn_layers.MBConvSamePadding¶
- class cutcutcodec.core.analysis.video.quality.uvq_google.custom_nn_layers.MBConvSamePadding(input_channels: int, expand_ratio: int, out_channels: int, kernel: int, stride: int, stochastic_depth_prob: float, norm_layer: ~collections.abc.Callable[[...], ~torch.nn.modules.module.Module] = functools.partial(<class 'torch.nn.modules.batchnorm.BatchNorm2d'>, eps=0.001, momentum=0.99), se_layer: ~collections.abc.Callable[[...], ~torch.nn.modules.module.Module] = <class 'torchvision.ops.misc.SqueezeExcitation'>)[source]¶
Part of uvq model.
Initialize internal Module state, shared by both nn.Module and ScriptModule.