summaryrefslogtreecommitdiff
path: root/text_recognizer/networks/encoders/efficient_net
diff options
context:
space:
mode:
Diffstat (limited to 'text_recognizer/networks/encoders/efficient_net')
-rw-r--r--text_recognizer/networks/encoders/efficient_net/__init__.py0
-rw-r--r--text_recognizer/networks/encoders/efficient_net/block.py160
2 files changed, 0 insertions, 160 deletions
diff --git a/text_recognizer/networks/encoders/efficient_net/__init__.py b/text_recognizer/networks/encoders/efficient_net/__init__.py
deleted file mode 100644
index e69de29..0000000
--- a/text_recognizer/networks/encoders/efficient_net/__init__.py
+++ /dev/null
diff --git a/text_recognizer/networks/encoders/efficient_net/block.py b/text_recognizer/networks/encoders/efficient_net/block.py
deleted file mode 100644
index d9a0416..0000000
--- a/text_recognizer/networks/encoders/efficient_net/block.py
+++ /dev/null
@@ -1,160 +0,0 @@
-"""Mobile inverted residual block."""
-from typing import Tuple
-
-import torch
-from torch import nn, Tensor
-from torch.nn import functional as F
-
-from .utils import get_same_padding_conv2d
-
-
-class MBConvBlock(nn.Module):
- """Mobile Inverted Residual Bottleneck block."""
-
- def __init__(
- self,
- in_channels: int,
- kernel_size: int,
- stride: int,
- bn_momentum: float,
- bn_eps: float,
- se_ratio: float,
- id_skip: bool,
- expand_ratio: int,
- image_size: Tuple[int, int],
- ) -> None:
- super().__init__()
- self.kernel_size = kernel_size
- self.bn_momentum = bn_momentum
- self.bn_eps = bn_eps
- self.has_se = se_ratio is not None and 0.0 < se_ratio < 1.0
-
- out_channels = in_channels * expand_ratio
- self._inverted_bottleneck = (
- self._configure_inverted_bottleneck(
- image_size=image_size,
- in_channels=in_channels,
- out_channels=out_channels,
- )
- if expand_ratio != 1
- else None
- )
-
- self._depthwise = self._configure_depthwise(
- image_size=image_size,
- in_channels=in_channels,
- out_channels=out_channels,
- groups=out_channels,
- kernel_size=kernel_size,
- stride=stride,
- )
-
- image_size = calculate_output_image_size(image_size, stride)
- self._squeeze_excite = (
- self._configure_squeeze_excite(
- in_channels=out_channels, out_channels=out_channels, se_ratio=se_ratio
- )
- if self.has_se
- else None
- )
-
- self._pointwise = self._configure_pointwise(
- image_size=image_size, in_channels=out_channels, out_channels=out_channels
- )
-
- def _configure_inverted_bottleneck(
- self,
- image_size: Tuple[int, int],
- in_channels: int,
- out_channels: int,
- ) -> nn.Sequential:
- """Expansion phase."""
- Conv2d = get_same_padding_conv2d(image_size=image_size)
- return nn.Sequential(
- Conv2d(
- in_channels=in_channels,
- out_channels=out_channels,
- kernel_size=1,
- bias=False,
- ),
- nn.BatchNorm2d(
- num_features=out_channels, momentum=self.bn_momentum, eps=self.bn_eps
- ),
- nn.SiLU(inplace=True),
- )
-
- def _configure_depthwise(
- self,
- image_size: Tuple[int, int],
- in_channels: int,
- out_channels: int,
- groups: int,
- kernel_size: int,
- stride: int,
- ) -> nn.Sequential:
- Conv2d = get_same_padding_conv2d(image_size=image_size)
- return nn.Sequential(
- Conv2d(
- in_channels=in_channels,
- out_channels=out_channels,
- kernel_size=kernel_size,
- stride=stride,
- groups=groups,
- bias=False,
- ),
- nn.BatchNorm2d(
- num_features=out_channels, momentum=self.bn_momentum, eps=self.bn_eps
- ),
- nn.SiLU(inplace=True),
- )
-
- def _configure_squeeze_excite(
- self, in_channels: int, out_channels: int, se_ratio: float
- ) -> nn.Sequential:
- Conv2d = get_same_padding_conv2d(image_size=(1, 1))
- num_squeezed_channels = max(1, int(in_channels * se_ratio))
- return nn.Sequential(
- Conv2d(
- in_channels=in_channels,
- out_channels=num_squeezed_channels,
- kernel_size=1,
- ),
- nn.SiLU(inplace=True),
- Conv2d(
- in_channels=num_squeezed_channels,
- out_channels=out_channels,
- kernel_size=1,
- ),
- )
-
- def _configure_pointwise(
- self, image_size: Tuple[int, int], in_channels: int, out_channels: int
- ) -> nn.Sequential:
- Conv2d = get_same_padding_conv2d(image_size=image_size)
- return nn.Sequential(
- Conv2d(
- in_channels=in_channels,
- out_channels=out_channels,
- kernel_size=1,
- bias=False,
- ),
- nn.BatchNorm2d(
- num_features=out_channels, momentum=self.bn_momentum, eps=self.bn_eps
- ),
- )
-
- def forward(self, x: Tensor, drop_connection_rate: Optional[float]) -> Tensor:
- residual = x
- if self._inverted_bottleneck is not None:
- x = self._inverted_bottleneck(x)
-
- x = self._depthwise(x)
-
- if self._squeeze_excite is not None:
- x_squeezed = F.adaptive_avg_pool2d(x, 1)
- x_squeezed = self._squeeze_excite(x)
- x = torch.sigmoid(x_squeezed) * x
-
- x = self._pointwise(x)
-
- # Stochastic depth