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.

Sign up for GitHub

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

[Features] Conv3dNet and PermuteTransform #1398

Merged
merged 15 commits into from
Sep 16, 2023
Merged

[Features] Conv3dNet and PermuteTransform #1398

Changes from 1 commit
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
59bb745
[Fix] RoundRobinWriter.extend() index error
xmaples Jun 19, 2023
fa52e35
[Fix] RoundRobinWriter.extend() index error
xmaples Jun 19, 2023
4d2c6df
init
vmoens Jun 19, 2023
821f7a0
Merge pull request #2 from vmoens/xmaples_mains2
xmaples Jun 19, 2023
83cd864
Merge branch 'pytorch:main' into main
xmaples Jul 19, 2023
9aac3ff
[Feat.] Conv3dNet, PermuteTransform
xmaples Jul 19, 2023
5b45d10
error msg
xmaples Jul 20, 2023
4ef3753
doc
xmaples Jul 20, 2023
290d8b3
by depth
xmaples Jul 20, 2023
1d2723c
doc
xmaples Jul 20, 2023
8ddbc09
dims check
xmaples Jul 20, 2023
6e00f6c
more tests
xmaples Jul 20, 2023
519975b
Merge branch 'main' into HEAD
vmoens Sep 7, 2023
394690e
lint
vmoens Sep 7, 2023
3fcd563
Merge branch 'main' into edit_conv3d
vmoens Sep 15, 2023
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
Prev Previous commit
Next Next commit
doc 
Co-authored-by: Vincent Moens <vincentmoens@gmail.com>
  • Loading branch information
@xmaples @vmoens
xmaples and vmoens authored Jul 20, 2023
commit 1d2723c7f362c72b4b1e1f4393a1fbcb5a00db03
2 changes: 1 addition & 1 deletion torchrl/modules/models/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -498,7 +498,7 @@ class Conv3dNet(nn.Sequential):
num_cells (int or Sequence[int], optional): number of cells of every layer in between the input and output. If
an integer is provided, every layer will have the same number of cells. If an iterable is provided,
the linear layers out_features will match the content of num_cells.
default: [32, 32, 32];
default: ``[32, 32, 32]`` or ``[32] * depth` is depth is not ``None``.
kernel_sizes (int, Sequence[Union[int, Sequence[int]]]): Kernel size(s) of the conv network. If iterable, the length must match the
depth, defined by the num_cells or depth arguments.
strides (int or Sequence[int]): Stride(s) of the conv network. If iterable, the length must match the
Expand Down