124 lines
4.5 KiB
Python
124 lines
4.5 KiB
Python
from typing import Union, Tuple
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
|
|
from .utils.logger import DummyLogger
|
|
|
|
|
|
class LayerInfo():
|
|
def __init__(self):
|
|
self.memory = 0.0
|
|
self.ops = 0.0
|
|
self.output = 0.0
|
|
|
|
|
|
class Layer(nn.Module):
|
|
# Default layer arguments
|
|
ACTIVATION = F.leaky_relu
|
|
|
|
BATCH_NORM = True
|
|
BATCH_NORM_TRAINING = True
|
|
BATCH_NORM_MOMENTUM = 0.01
|
|
|
|
IS_TRAINING = False
|
|
METRICS = False
|
|
VERBOSE = 0
|
|
LOGGER = DummyLogger()
|
|
|
|
def __init__(self, activation, batch_norm):
|
|
super().__init__()
|
|
self.name = 'Layer'
|
|
self.info = LayerInfo()
|
|
|
|
# Preload default
|
|
self.activation = Layer.ACTIVATION if activation == 0 else activation
|
|
self.batch_norm = Layer.BATCH_NORM if batch_norm is None else batch_norm
|
|
|
|
def forward(self, input_data: torch.Tensor) -> torch.Tensor:
|
|
output = input_data
|
|
if self.activation is not None:
|
|
output = self.activation(output)
|
|
if self.batch_norm is not None:
|
|
output = self.batch_norm(output)
|
|
return output
|
|
|
|
|
|
class Linear(Layer):
|
|
def __init__(self, in_channels: int, out_channels: int, activation=0, batch_norm=None, **kwargs):
|
|
super().__init__(activation, batch_norm)
|
|
|
|
self.fc = nn.Linear(in_channels, out_channels, **kwargs)
|
|
self.batch_norm = nn.BatchNorm1d(
|
|
out_channels,
|
|
momentum=Layer.BATCH_NORM_MOMENTUM,
|
|
track_running_stats=Layer.BATCH_NORM_TRAINING) if self.batch_norm else None
|
|
|
|
def forward(self, input_data: torch.Tensor) -> torch.Tensor:
|
|
return super().forward(self.fc(input_data))
|
|
|
|
|
|
class Conv1d(Layer):
|
|
def __init__(self, in_channels: int, out_channels: int, kernel_size: int = 3,
|
|
stride: Union[int, Tuple[int, int]] = 1, activation=0, batch_norm=None, **kwargs):
|
|
super().__init__(activation, batch_norm)
|
|
|
|
self.conv = nn.Conv1d(in_channels, out_channels, kernel_size, stride=stride,
|
|
bias=not self.batch_norm, **kwargs)
|
|
self.batch_norm = nn.BatchNorm1d(
|
|
out_channels,
|
|
momentum=Layer.BATCH_NORM_MOMENTUM,
|
|
track_running_stats=Layer.BATCH_NORM_TRAINING) if self.batch_norm else None
|
|
|
|
def forward(self, input_data: torch.Tensor) -> torch.Tensor:
|
|
return super().forward(self.conv(input_data))
|
|
|
|
|
|
class Conv2d(Layer):
|
|
def __init__(self, in_channels: int, out_channels: int, kernel_size: int = 3,
|
|
stride: Union[int, Tuple[int, int]] = 1, activation=0, batch_norm=None, **kwargs):
|
|
super().__init__(activation, batch_norm)
|
|
|
|
self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride=stride,
|
|
bias=not self.batch_norm, **kwargs)
|
|
self.batch_norm = nn.BatchNorm2d(
|
|
out_channels,
|
|
momentum=Layer.BATCH_NORM_MOMENTUM,
|
|
track_running_stats=not Layer.BATCH_NORM_TRAINING) if self.batch_norm else None
|
|
|
|
def forward(self, input_data: torch.Tensor) -> torch.Tensor:
|
|
return super().forward(self.conv(input_data))
|
|
|
|
|
|
class Conv3d(Layer):
|
|
def __init__(self, in_channels: int, out_channels: int, kernel_size: int = 3,
|
|
stride: Union[int, Tuple[int, int]] = 1, activation=0, batch_norm=None, **kwargs):
|
|
super().__init__(activation, batch_norm)
|
|
|
|
self.conv = nn.Conv3d(in_channels, out_channels, kernel_size, stride=stride,
|
|
bias=not self.batch_norm, **kwargs)
|
|
self.batch_norm = nn.BatchNorm3d(
|
|
out_channels,
|
|
momentum=Layer.BATCH_NORM_MOMENTUM,
|
|
track_running_stats=Layer.BATCH_NORM_TRAINING) if self.batch_norm else None
|
|
|
|
def forward(self, input_data: torch.Tensor) -> torch.Tensor:
|
|
return super().forward(self.conv(input_data))
|
|
|
|
|
|
class Deconv2d(Layer):
|
|
def __init__(self, in_channels: int, out_channels: int, kernel_size: int = 3,
|
|
stride: Union[int, Tuple[int, int]] = 1, activation=0, batch_norm=None, **kwargs):
|
|
super().__init__(activation, batch_norm)
|
|
|
|
self.deconv = nn.ConvTranspose2d(
|
|
in_channels, out_channels, kernel_size, stride=stride,
|
|
bias=not self.batch_norm, **kwargs)
|
|
self.batch_norm = nn.BatchNorm2d(
|
|
out_channels,
|
|
momentum=Layer.BATCH_NORM_MOMENTUM,
|
|
track_running_stats=not Layer.BATCH_NORM_TRAINING) if self.batch_norm else None
|
|
|
|
def forward(self, input_data: torch.Tensor) -> torch.Tensor:
|
|
return super().forward(self.deconv(input_data))
|