Layers and other models#

Layers#

class kornia.feature.FilterResponseNorm2d(num_features, eps=1e-6, is_bias=True, is_scale=True, is_eps_leanable=False)[source]#

Feature Response Normalization layer from ‘Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks’, see [SK20] for more details.

\[y = \gamma \times \frac{x}{\sqrt{\mathrm{E}[x^2]} + |\epsilon|} + \beta\]

Parameters:

num_features (int) – number of channels
eps (float, optional) – normalization constant Default: 1e-6
is_bias (bool, optional) – use bias Default: True
is_scale (bool, optional) – use scale Default: True
drop_rate – dropout rate,
is_eps_leanable (bool, optional) – if eps is learnable Default: False

Returns:

Normalized features

Return type:

torch.Tensor

Shape:

Input: \((B, \text{num_features}, H, W)\)
Output: \((B, \text{num_features}, H, W)\)

class kornia.feature.TLU(num_features)[source]#

TLU layer from ‘Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks, see [SK20] for more details. \({\tau}\) is learnable per channel.

\[y = \max(x, {\tau})\]

Parameters:: num_features (int) – number of channels
Returns:: torch.Tensor

Shape:

Input: \((B, \text{num_features}, H, W)\)
Output: \((B, \text{num_features}, H, W)\)

Fast moving objects#

class kornia.feature.DeFMO(pretrained=False)[source]#

nn.Module that disentangle a fast-moving object from the background and performs deblurring.

This is based on the original code from paper “DeFMO: Deblurring and Shape Recovery: of Fast Moving Objects”. See [ROF+21] for more details.

Parameters:: pretrained (bool, optional) – Download and set pretrained weights to the model. Default: false.
Returns:: Temporal super-resolution without background.

Shape:

Input: (B, 6, H, W)
Output: (B, S, 4, H, W)

Examples

>>> import kornia
>>> input = torch.rand(2, 6, 240, 320)
>>> defmo = kornia.feature.DeFMO()
>>> tsr_nobgr = defmo(input) # 2x24x4x240x320

forward(input_data)[source]#

Deblur a fast-moving object into a sequence of RGBA sub-frames.

Parameters:: input_data (Tensor) – Tensor with shape \((B, 6, H, W)\) containing the blurred RGB image concatenated with an RGB background estimate.
Return type:: Tensor
Returns:: Tensor with shape \((B, T, 4, H, W)\), where T is the number of temporal sub-frames and 4 stores red, green, blue, and alpha channels.