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()
