towhee.models.cvnet.resnet¶

Functions

Retrieves the transformation function by name.

Classes

`BasicTransform`	Basic transformation: 3x3, BN, ReLU, 3x3, BN.
`BottleneckTransform`	Bottleneck transformation: 1x1, BN, ReLU, 3x3, BN, ReLU, 1x1, BN.
`GeneralizedMeanPooling`	Applies a 2D power-average adaptive pooling over an input signal composed of several input planes. The function computed is: \(f(X) = pow(sum(pow(X, p)), 1/p)\) - At p = infinity, one gets Max Pooling - At p = 1, one gets Average Pooling The output is of size H x W, for any input size. The number of output features is equal to the number of input planes. :param output_size: the target output size of the image of the form H x W. Can be a tuple (H, W) or a single H for a square image H x H H and W can be either a `int`, or `None` which means the size will be the same as that of the input.
`GeneralizedMeanPoolingP`	Same, but norm is trainable
`GlobalHead`
`ResBlock`	Residual block: x + F(x).
`ResNet`	ResNet model.
`ResStage`	Stage of ResNet.
`ResStemIN`	ResNet stem for ImageNet: 7x7, BN, ReLU, MaxPool.