MiniVGG

class mmocr.models.textrecog.MiniVGG(leaky_relu=True, input_channels=3, init_cfg=[{'type': 'Xavier', 'layer': 'Conv2d'}, {'type': 'Uniform', 'layer': 'BatchNorm2d'}])

A mini VGG backbone for text recognition, modified from `VGG-VeryDeep.

<https://arxiv.org/pdf/1409.1556.pdf>`_

Parameters

• leaky_relu (bool) – Use leakyRelu or not.

• input_channels (int) – Number of channels of input image tensor.

forward(x)

Parameters

x (Tensor) – Images of shape \((N, C, H, W)\).

Returns

The feature Tensor of shape \((N, 512, H/32, (W/4+1)\).

Return type

Tensor