summaryrefslogtreecommitdiff
path: root/text_recognizer/networks/vqvae
diff options
context:
space:
mode:
Diffstat (limited to 'text_recognizer/networks/vqvae')
-rw-r--r--text_recognizer/networks/vqvae/decoder.py18
-rw-r--r--text_recognizer/networks/vqvae/encoder.py12
2 files changed, 25 insertions, 5 deletions
diff --git a/text_recognizer/networks/vqvae/decoder.py b/text_recognizer/networks/vqvae/decoder.py
index 8847aba..67ed0d9 100644
--- a/text_recognizer/networks/vqvae/decoder.py
+++ b/text_recognizer/networks/vqvae/decoder.py
@@ -44,7 +44,12 @@ class Decoder(nn.Module):
# Configure encoder.
self.decoder = self._build_decoder(
- channels, kernel_sizes, strides, num_residual_layers, activation, dropout,
+ channels,
+ kernel_sizes,
+ strides,
+ num_residual_layers,
+ activation,
+ dropout,
)
def _build_decompression_block(
@@ -73,7 +78,9 @@ class Decoder(nn.Module):
)
if i < len(self.upsampling):
- modules.append(nn.Upsample(size=self.upsampling[i]),)
+ modules.append(
+ nn.Upsample(size=self.upsampling[i]),
+ )
if dropout is not None:
modules.append(dropout)
@@ -102,7 +109,12 @@ class Decoder(nn.Module):
) -> nn.Sequential:
self.res_block.append(
- nn.Conv2d(self.embedding_dim, channels[0], kernel_size=1, stride=1,)
+ nn.Conv2d(
+ self.embedding_dim,
+ channels[0],
+ kernel_size=1,
+ stride=1,
+ )
)
# Bottleneck module.
diff --git a/text_recognizer/networks/vqvae/encoder.py b/text_recognizer/networks/vqvae/encoder.py
index d3adac5..ede5c31 100644
--- a/text_recognizer/networks/vqvae/encoder.py
+++ b/text_recognizer/networks/vqvae/encoder.py
@@ -11,7 +11,10 @@ from text_recognizer.networks.vqvae.vector_quantizer import VectorQuantizer
class _ResidualBlock(nn.Module):
def __init__(
- self, in_channels: int, out_channels: int, dropout: Optional[Type[nn.Module]],
+ self,
+ in_channels: int,
+ out_channels: int,
+ dropout: Optional[Type[nn.Module]],
) -> None:
super().__init__()
self.block = [
@@ -135,7 +138,12 @@ class Encoder(nn.Module):
)
encoder.append(
- nn.Conv2d(channels[-1], self.embedding_dim, kernel_size=1, stride=1,)
+ nn.Conv2d(
+ channels[-1],
+ self.embedding_dim,
+ kernel_size=1,
+ stride=1,
+ )
)
return nn.Sequential(*encoder)