Source code for segmentation_models_pytorch.decoders.manet.model

import warnings
from typing import Any, Dict, Optional, Union, Sequence, Callable

from segmentation_models_pytorch.base import (
    ClassificationHead,
    SegmentationHead,
    SegmentationModel,
)
from segmentation_models_pytorch.encoders import get_encoder
from segmentation_models_pytorch.base.hub_mixin import supports_config_loading

from .decoder import MAnetDecoder


[docs] class MAnet(SegmentationModel): """MAnet_ : Multi-scale Attention Net. The MA-Net can capture rich contextual dependencies based on the attention mechanism, using two blocks: - Position-wise Attention Block (PAB), which captures the spatial dependencies between pixels in a global view - Multi-scale Fusion Attention Block (MFAB), which captures the channel dependencies between any feature map by multi-scale semantic feature fusion Args: encoder_name: Name of the classification model that will be used as an encoder (a.k.a backbone) to extract features of different spatial resolution encoder_depth: A number of stages used in encoder in range [3, 5]. Each stage generate features two times smaller in spatial dimensions than previous one (e.g. for depth 0 we will have features with shapes [(N, C, H, W),], for depth 1 - [(N, C, H, W), (N, C, H // 2, W // 2)] and so on). Default is 5 encoder_weights: One of **None** (random initialization), **"imagenet"** (pre-training on ImageNet) and other pretrained weights (see table with available weights for each encoder_name) decoder_channels: List of integers which specify **in_channels** parameter for convolutions used in decoder. Length of the list should be the same as **encoder_depth** decoder_use_norm: Specifies normalization between Conv2D and activation. Accepts the following types: - **True**: Defaults to `"batchnorm"`. - **False**: No normalization (`nn.Identity`). - **str**: Specifies normalization type using default parameters. Available values: `"batchnorm"`, `"identity"`, `"layernorm"`, `"instancenorm"`, `"inplace"`. - **dict**: Fully customizable normalization settings. Structure: ```python {"type": <norm_type>, **kwargs} ``` where `norm_name` corresponds to normalization type (see above), and `kwargs` are passed directly to the normalization layer as defined in PyTorch documentation. **Example**: ```python decoder_use_norm={"type": "layernorm", "eps": 1e-2} ``` decoder_pab_channels: A number of channels for PAB module in decoder. Default is 64. decoder_interpolation: Interpolation mode used in decoder of the model. Available options are **"nearest"**, **"bilinear"**, **"bicubic"**, **"area"**, **"nearest-exact"**. Default is **"nearest"**. in_channels: A number of input channels for the model, default is 3 (RGB images) classes: A number of classes for output mask (or you can think as a number of channels of output mask) activation: An activation function to apply after the final convolution layer. Available options are **"sigmoid"**, **"softmax"**, **"logsoftmax"**, **"tanh"**, **"identity"**, **callable** and **None**. Default is **None**. aux_params: Dictionary with parameters of the auxiliary output (classification head). Auxiliary output is build on top of encoder if **aux_params** is not **None** (default). Supported params: - classes (int): A number of classes - pooling (str): One of "max", "avg". Default is "avg" - dropout (float): Dropout factor in [0, 1) - activation (str): An activation function to apply "sigmoid"/"softmax" (could be **None** to return logits) kwargs: Arguments passed to the encoder class ``__init__()`` function. Applies only to ``timm`` models. Keys with ``None`` values are pruned before passing. Returns: ``torch.nn.Module``: **MAnet** .. _MAnet: https://ieeexplore.ieee.org/abstract/document/9201310 """ @supports_config_loading def __init__( self, encoder_name: str = "resnet34", encoder_depth: int = 5, encoder_weights: Optional[str] = "imagenet", decoder_use_norm: Union[bool, str, Dict[str, Any]] = "batchnorm", decoder_channels: Sequence[int] = (256, 128, 64, 32, 16), decoder_pab_channels: int = 64, decoder_interpolation: str = "nearest", in_channels: int = 3, classes: int = 1, activation: Optional[Union[str, Callable]] = None, aux_params: Optional[dict] = None, **kwargs: dict[str, Any], ): super().__init__() decoder_use_batchnorm = kwargs.pop("decoder_use_batchnorm", None) if decoder_use_batchnorm is not None: warnings.warn( "The usage of decoder_use_batchnorm is deprecated. Please modify your code for decoder_use_norm", DeprecationWarning, stacklevel=2, ) decoder_use_norm = decoder_use_batchnorm self.encoder = get_encoder( encoder_name, in_channels=in_channels, depth=encoder_depth, weights=encoder_weights, **kwargs, ) self.decoder = MAnetDecoder( encoder_channels=self.encoder.out_channels, decoder_channels=decoder_channels, n_blocks=encoder_depth, use_norm=decoder_use_norm, pab_channels=decoder_pab_channels, interpolation_mode=decoder_interpolation, ) self.segmentation_head = SegmentationHead( in_channels=decoder_channels[-1], out_channels=classes, activation=activation, kernel_size=3, ) if aux_params is not None: self.classification_head = ClassificationHead( in_channels=self.encoder.out_channels[-1], **aux_params ) else: self.classification_head = None self.name = "manet-{}".format(encoder_name) self.initialize()