mmagic.models.editors.tdan
¶
Package Contents¶
Classes¶
TDAN model for video super-resolution. |
|
TDAN network structure for video super-resolution. |
- class mmagic.models.editors.tdan.TDAN(generator, pixel_loss, lq_pixel_loss, train_cfg=None, test_cfg=None, init_cfg=None, data_preprocessor=None)[源代码]¶
Bases:
mmagic.models.BaseEditModel
TDAN model for video super-resolution.
- Paper:
TDAN: Temporally-Deformable Alignment Network for Video Super- Resolution, CVPR, 2020
- 参数
generator (dict) – Config for the generator structure.
pixel_loss (dict) – Config for pixel-wise loss.
lq_pixel_loss (dict) – Config for pixel-wise loss for the LQ images.
train_cfg (dict) – Config for training. Default: None.
test_cfg (dict) – Config for testing. Default: None.
init_cfg (dict, optional) – The weight initialized config for
BaseModule
.data_preprocessor (dict, optional) – The pre-process config of
BaseDataPreprocessor
.
- forward_train(inputs, data_samples=None, **kwargs)¶
Forward training. Returns dict of losses of training.
- 参数
inputs (torch.Tensor) – batch input tensor collated by
data_preprocessor
.data_samples (List[BaseDataElement], optional) – data samples collated by
data_preprocessor
.
- 返回
Dict of losses.
- 返回类型
dict
- forward_tensor(inputs, data_samples=None, training=False, **kwargs)¶
Forward tensor. Returns result of simple forward.
- 参数
inputs (torch.Tensor) – batch input tensor collated by
data_preprocessor
.data_samples (List[BaseDataElement], optional) – data samples collated by
data_preprocessor
.training (bool) – Whether is training. Default: False.
- 返回
- results of forward inference and
forward train.
- 返回类型
(Tensor | List[Tensor])
- class mmagic.models.editors.tdan.TDANNet(in_channels=3, mid_channels=64, out_channels=3, num_blocks_before_align=5, num_blocks_after_align=10)[源代码]¶
Bases:
mmengine.model.BaseModule
TDAN network structure for video super-resolution.
Support only x4 upsampling.
- Paper:
TDAN: Temporally-Deformable Alignment Network for Video Super- Resolution, CVPR, 2020
- 参数
in_channels (int) – Number of channels of the input image. Default: 3.
mid_channels (int) – Number of channels of the intermediate features. Default: 64.
out_channels (int) – Number of channels of the output image. Default: 3.
num_blocks_before_align (int) – Number of residual blocks before temporal alignment. Default: 5.
num_blocks_after_align (int) – Number of residual blocks after temporal alignment. Default: 10.
- forward(lrs)¶
Forward function for TDANNet.
- 参数
lrs (Tensor) – Input LR sequence with shape (n, t, c, h, w).
- 返回
Output HR image with shape (n, c, 4h, 4w) and aligned LR images with shape (n, t, c, h, w).
- 返回类型
tuple[Tensor]