Skip to content

Commit

Permalink
Merge pull request #541 from stweil/typos
Browse files Browse the repository at this point in the history
Fix some typos
  • Loading branch information
mittagessen authored Sep 4, 2023
2 parents cc1238a + 5e8d15a commit b89cfb2
Show file tree
Hide file tree
Showing 5 changed files with 6 additions and 6 deletions.
4 changes: 2 additions & 2 deletions docs/vgsl.rst
Original file line number Diff line number Diff line change
Expand Up @@ -114,7 +114,7 @@ recurrent layers and a linear projection.
1 groupnorm 8 groups
2 parallel execute 2.0 and 2.1 in parallel
2.0 identity
2.1 serial exectute 2.1.0 to 2.1.2 in sequence
2.1 serial execute 2.1.0 to 2.1.2 in sequence
2.1.0 conv kernel 3 x 3 stride 2 x 2 filters 64 activation r
2.1.1 groupnorm 8 groups
2.1.2 transposed convolution kernel 3 x 3 stride 2 x 2 filters 2 activation r
Expand All @@ -128,7 +128,7 @@ the image back to its original size. This is done in a parallel block, where the
other branch simply passes through the output of the first convolution layer.
The input of the last convolutional layer is then the output of the two branches
of the parallel block concatenated, i.e. the output of the first
convolutional layer together with the ouput of the transposed convolutional layer,
convolutional layer together with the output of the transposed convolutional layer,
giving `32 + 32 = 64` feature dimensions.

Convolutional Layers
Expand Down
2 changes: 1 addition & 1 deletion kraken/ketos/pretrain.py
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@
@click.option('--lag',
show_default=True,
default=RECOGNITION_PRETRAIN_HYPER_PARAMS['lag'],
help='Number of evaluations (--report frequence) to wait before stopping training without improvement')
help='Number of evaluations (--report frequency) to wait before stopping training without improvement')
@click.option('--min-delta',
show_default=True,
default=RECOGNITION_PRETRAIN_HYPER_PARAMS['min_delta'],
Expand Down
2 changes: 1 addition & 1 deletion kraken/ketos/recognition.py
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,7 @@
@click.option('--lag',
show_default=True,
default=RECOGNITION_HYPER_PARAMS['lag'],
help='Number of evaluations (--report frequence) to wait before stopping training without improvement')
help='Number of evaluations (--report frequency) to wait before stopping training without improvement')
@click.option('--min-delta',
show_default=True,
default=RECOGNITION_HYPER_PARAMS['min_delta'],
Expand Down
2 changes: 1 addition & 1 deletion kraken/ketos/segmentation.py
Original file line number Diff line number Diff line change
Expand Up @@ -90,7 +90,7 @@ def _validate_merging(ctx, param, value):
@click.option('--lag',
show_default=True,
default=SEGMENTATION_HYPER_PARAMS['lag'],
help='Number of evaluations (--report frequence) to wait before stopping training without improvement')
help='Number of evaluations (--report frequency) to wait before stopping training without improvement')
@click.option('--min-delta',
show_default=True,
default=SEGMENTATION_HYPER_PARAMS['min_delta'],
Expand Down
2 changes: 1 addition & 1 deletion kraken/lib/layers.py
Original file line number Diff line number Diff line change
Expand Up @@ -805,7 +805,7 @@ def forward(self, inputs: torch.Tensor, seq_len: Optional[torch.Tensor] = None,

def get_shape(self, input: Tuple[int, int, int, int], target_shape: Optional[Tuple[int, int, int, int]] = None) -> Tuple[int, int, int, int]:
if self.transposed:
""" For transposed convolution, there is some flexibilty. """
""" For transposed convolution, there is some flexibility. """
min_y = int((input[2] - 1) * self.stride[0] - 2 * self.padding[0] + self.dilation[0] * (self.kernel_size[0] - 1) + 1 if input[2] != 0 else 0)
target_y = min_y if not target_shape or target_shape[2] == 0 else target_shape[2]
min_x = int((input[3] - 1) * self.stride[1] - 2 * self.padding[1] + self.dilation[1] * (self.kernel_size[1] - 1) + 1 if input[3] != 0 else 0)
Expand Down

0 comments on commit b89cfb2

Please sign in to comment.