File size: 4,518 Bytes
2a13495
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
from typing import Optional, Union

from segmentation_models_pytorch.encoders import get_encoder
from segmentation_models_pytorch.base import (
    SegmentationModel,
    SegmentationHead,
    ClassificationHead,
)
from .decoder import PSPDecoder


class PSPNet(SegmentationModel):
    """PSPNet_ is a fully convolution neural network for image semantic segmentation. Consist of
    *encoder* and *Spatial Pyramid* (decoder). Spatial Pyramid build on top of encoder and does not
    use "fine-features" (features of high spatial resolution). PSPNet can be used for multiclass segmentation
    of high resolution images, however it is not good for detecting small objects and producing accurate,
    pixel-level mask.

    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)
        psp_out_channels: A number of filters in Spatial Pyramid
        psp_use_batchnorm: If **True**, BatchNorm2d layer between Conv2D and Activation layers
            is used. If **"inplace"** InplaceABN will be used, allows to decrease memory consumption.
            Available options are **True, False, "inplace"**
        psp_dropout: Spatial dropout rate in [0, 1) used in Spatial Pyramid
        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**
        upsampling: Final upsampling factor. Default is 8 to preserve input-output spatial shape identity
        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)

    Returns:
        ``torch.nn.Module``: **PSPNet**

    .. _PSPNet:
        https://arxiv.org/abs/1612.01105
    """

    def __init__(
        self,
        encoder_name: str = "resnet34",
        encoder_weights: Optional[str] = "imagenet",
        encoder_depth: int = 3,
        psp_out_channels: int = 512,
        psp_use_batchnorm: bool = True,
        psp_dropout: float = 0.2,
        in_channels: int = 3,
        classes: int = 1,
        activation: Optional[Union[str, callable]] = None,
        upsampling: int = 8,
        aux_params: Optional[dict] = None,
    ):
        super().__init__()

        self.encoder = get_encoder(
            encoder_name,
            in_channels=in_channels,
            depth=encoder_depth,
            weights=encoder_weights,
        )

        self.decoder = PSPDecoder(
            encoder_channels=self.encoder.out_channels,
            use_batchnorm=psp_use_batchnorm,
            out_channels=psp_out_channels,
            dropout=psp_dropout,
        )

        self.segmentation_head = SegmentationHead(
            in_channels=psp_out_channels,
            out_channels=classes,
            kernel_size=3,
            activation=activation,
            upsampling=upsampling,
        )

        if aux_params:
            self.classification_head = ClassificationHead(
                in_channels=self.encoder.out_channels[-1], **aux_params
            )
        else:
            self.classification_head = None

        self.name = "psp-{}".format(encoder_name)
        self.initialize()