Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Docs] Fix docstring for 3d flate #925

Merged
merged 1 commit into from
Jun 13, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions mmaction/models/backbones/resnet3d.py
Original file line number Diff line number Diff line change
Expand Up @@ -362,7 +362,7 @@ class ResNet3d(nn.Module):
not freezing any parameters. Default: -1.
inflate (Sequence[int]): Inflate Dims of each block.
Default: (1, 1, 1, 1).
inflate_style (str): ``3x1x1`` or ``1x1x1``. which determines the
inflate_style (str): ``3x1x1`` or ``3x3x3``. which determines the
kernel sizes and padding strides for conv1 and conv2 in each block.
Default: '3x1x1'.
conv_cfg (dict): Config for conv layers. required keys are ``type``
Expand Down Expand Up @@ -544,7 +544,7 @@ def make_res_layer(block,
Default: ``pytorch``.
inflate (int | Sequence[int]): Determine whether to inflate
for each block. Default: 1.
inflate_style (str): ``3x1x1`` or ``1x1x1``. which determines
inflate_style (str): ``3x1x1`` or ``3x3x3``. which determines
the kernel sizes and padding strides for conv1 and conv2
in each block. Default: '3x1x1'.
non_local (int | Sequence[int]): Determine whether to apply
Expand Down Expand Up @@ -879,7 +879,7 @@ class ResNet3dLayer(nn.Module):
the first 1x1 conv layer. Default: 'pytorch'.
all_frozen (bool): Frozen all modules in the layer. Default: False.
inflate (int): Inflate Dims of each block. Default: 1.
inflate_style (str): ``3x1x1`` or ``1x1x1``. which determines the
inflate_style (str): ``3x1x1`` or ``3x3x3``. which determines the
kernel sizes and padding strides for conv1 and conv2 in each block.
Default: '3x1x1'.
conv_cfg (dict): Config for conv layers. required keys are ``type``
Expand Down
2 changes: 1 addition & 1 deletion mmaction/models/backbones/resnet3d_csn.py
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ class ResNet3dCSN(ResNet3d):
norm_cfg (dict): Config for norm layers. required keys are `type` and
`requires_grad`.
Default: dict(type='BN3d', requires_grad=True, eps=1e-3).
inflate_style (str): `3x1x1` or `1x1x1`. which determines the kernel
inflate_style (str): `3x1x1` or `3x3x3`. which determines the kernel
sizes and padding strides for conv1 and conv2 in each block.
Default: '3x3x3'.
bottleneck_mode (str): Determine which ways to factorize a 3D
Expand Down
2 changes: 1 addition & 1 deletion mmaction/models/backbones/resnet3d_slowfast.py
Original file line number Diff line number Diff line change
Expand Up @@ -120,7 +120,7 @@ def make_res_layer(self,
Default: ``pytorch``.
inflate (int | Sequence[int]): Determine whether to inflate
for each block. Default: 1.
inflate_style (str): ``3x1x1`` or ``1x1x1``. which determines
inflate_style (str): ``3x1x1`` or ``3x3x3``. which determines
the kernel sizes and padding strides for conv1 and
conv2 in each block. Default: ``3x1x1``.
non_local (int | Sequence[int]): Determine whether to apply
Expand Down