PaddleX/paddlex/paddleseg/models/layers/layer_libs.py

# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import os

import paddle
import paddle.nn as nn
import paddle.nn.functional as F


def SyncBatchNorm(*args, **kwargs):
    """In cpu environment nn.SyncBatchNorm does not have kernel so use nn.BatchNorm2D instead"""
    if paddle.get_device() == 'cpu' or os.environ.get(
            'PADDLESEG_EXPORT_STAGE'):
        return nn.BatchNorm2D(*args, **kwargs)
    else:
        return nn.SyncBatchNorm(*args, **kwargs)


class ConvBNReLU(nn.Layer):
    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size,
                 padding='same',
                 **kwargs):
        super().__init__()

        self._conv = nn.Conv2D(
            in_channels, out_channels, kernel_size, padding=padding, **kwargs)

        self._batch_norm = SyncBatchNorm(out_channels)

    def forward(self, x):
        x = self._conv(x)
        x = self._batch_norm(x)
        x = F.relu(x)
        return x


class ConvBN(nn.Layer):
    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size,
                 padding='same',
                 **kwargs):
        super().__init__()
        self._conv = nn.Conv2D(
            in_channels, out_channels, kernel_size, padding=padding, **kwargs)
        self._batch_norm = SyncBatchNorm(out_channels)

    def forward(self, x):
        x = self._conv(x)
        x = self._batch_norm(x)
        return x


class ConvReLUPool(nn.Layer):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.conv = nn.Conv2D(
            in_channels,
            out_channels,
            kernel_size=3,
            stride=1,
            padding=1,
            dilation=1)

    def forward(self, x):
        x = self.conv(x)
        x = F.relu(x)
        x = F.pool2d(x, pool_size=2, pool_type="max", pool_stride=2)
        return x


class SeparableConvBNReLU(nn.Layer):
    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size,
                 padding='same',
                 **kwargs):
        super().__init__()
        self.depthwise_conv = ConvBN(
            in_channels,
            out_channels=in_channels,
            kernel_size=kernel_size,
            padding=padding,
            groups=in_channels,
            **kwargs)
        self.piontwise_conv = ConvBNReLU(
            in_channels, out_channels, kernel_size=1, groups=1)

    def forward(self, x):
        x = self.depthwise_conv(x)
        x = self.piontwise_conv(x)
        return x


class DepthwiseConvBN(nn.Layer):
    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size,
                 padding='same',
                 **kwargs):
        super().__init__()
        self.depthwise_conv = ConvBN(
            in_channels,
            out_channels=out_channels,
            kernel_size=kernel_size,
            padding=padding,
            groups=in_channels,
            **kwargs)

    def forward(self, x):
        x = self.depthwise_conv(x)
        return x


class AuxLayer(nn.Layer):
    """
    The auxiliary layer implementation for auxiliary loss.

    Args:
        in_channels (int): The number of input channels.
        inter_channels (int): The intermediate channels.
        out_channels (int): The number of output channels, and usually it is num_classes.
        dropout_prob (float, optional): The drop rate. Default: 0.1.
    """

    def __init__(self,
                 in_channels,
                 inter_channels,
                 out_channels,
                 dropout_prob=0.1):
        super().__init__()

        self.conv_bn_relu = ConvBNReLU(
            in_channels=in_channels,
            out_channels=inter_channels,
            kernel_size=3,
            padding=1)

        self.dropout = nn.Dropout(p=dropout_prob)

        self.conv = nn.Conv2D(
            in_channels=inter_channels,
            out_channels=out_channels,
            kernel_size=1)

    def forward(self, x):
        x = self.conv_bn_relu(x)
        x = self.dropout(x)
        x = self.conv(x)
        return x