File size: 7,481 Bytes
f1dd031
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
"""
Author: Siyuan Li
Licensed: Apache-2.0 License
"""

from typing import Any, Dict, List, Tuple

import torch
from mmdet.registry import MODELS
from mmengine.model import BaseModule
from torch.nn import functional as F

from ..sam.image_encoder import ImageEncoderViT
from ..sam.mask_decoder import MaskDecoder
from ..sam.prompt_encoder import PromptEncoder


@MODELS.register_module()
class SamMasa(BaseModule):
    mask_threshold: float = 0.0
    image_format: str = "RGB"

    def __init__(
        self,
        backbone: ImageEncoderViT,
        prompt_encoder: PromptEncoder,
        mask_decoder: MaskDecoder,
        pixel_mean: List[float] = [123.675, 116.28, 103.53],
        pixel_std: List[float] = [58.395, 57.12, 57.375],
        **kwargs
    ) -> None:
        """
        SAM predicts object masks from an image and input prompts.

        Arguments:
          backbone (ImageEncoderViT): The backbone used to encode the
            image into image embeddings that allow for efficient mask prediction.
          prompt_encoder (PromptEncoder): Encodes various types of input prompts.
          mask_decoder (MaskDecoder): Predicts masks from the image embeddings
            and encoded prompts.
          pixel_mean (list(float)): Mean values for normalizing pixels in the input image.
          pixel_std (list(float)): Std values for normalizing pixels in the input image.
        """
        super().__init__(**kwargs)
        if backbone is not None:
            self.backbone = MODELS.build(backbone)

        if prompt_encoder is not None:
            self.prompt_encoder = MODELS.build(prompt_encoder)
        else:
            self.prompt_encoder = None

        if mask_decoder is not None:
            self.mask_decoder = MODELS.build(mask_decoder)
        else:
            self.mask_decoder = None

        self.register_buffer(
            "pixel_mean", torch.Tensor(pixel_mean).view(-1, 1, 1), False
        )
        self.register_buffer("pixel_std", torch.Tensor(pixel_std).view(-1, 1, 1), False)

    @property
    def device(self) -> Any:
        return self.pixel_mean.device

    @torch.no_grad()
    def forward(
        self, batched_input: List[Dict[str, Any]], multimask_output: bool,
    ) -> List[Dict[str, torch.Tensor]]:
        """
        Predicts masks end-to-end from provided images and prompts.
        If prompts are not known in advance, using SamPredictor is
        recommended over calling the model directly.

        Arguments:
          batched_input (list(dict)): A list over input images, each a
            dictionary with the following keys. A prompt key can be
            excluded if it is not present.
              'image': The image as a torch tensor in 3xHxW format,
                already transformed for input to the model.
              'original_size': (tuple(int, int)) The original size of
                the image before transformation, as (H, W).
              'point_coords': (torch.Tensor) Batched point prompts for
                this image, with shape BxNx2. Already transformed to the
                input frame of the model.
              'point_labels': (torch.Tensor) Batched labels for point prompts,
                with shape BxN.
              'boxes': (torch.Tensor) Batched box inputs, with shape Bx4.
                Already transformed to the input frame of the model.
              'mask_inputs': (torch.Tensor) Batched mask inputs to the model,
                in the form Bx1xHxW.
          multimask_output (bool): Whether the model should predict multiple
            disambiguating masks, or return a single mask.

        Returns:
          (list(dict)): A list over input images, where each element is
            as dictionary with the following keys.
              'masks': (torch.Tensor) Batched binary mask predictions,
                with shape BxCxHxW, where B is the number of input promts,
                C is determiend by multimask_output, and (H, W) is the
                original size of the image.
              'iou_predictions': (torch.Tensor) The model's predictions
                of mask quality, in shape BxC.
              'low_res_logits': (torch.Tensor) Low resolution logits with
                shape BxCxHxW, where H=W=256. Can be passed as mask input
                to subsequent iterations of prediction.
        """
        input_images = torch.stack(
            [self.preprocess(x["image"]) for x in batched_input], dim=0
        )
        image_embeddings = self.backbone(input_images)

        outputs = []
        for image_record, curr_embedding in zip(batched_input, image_embeddings):
            if "point_coords" in image_record:
                points = (image_record["point_coords"], image_record["point_labels"])
            else:
                points = None
            sparse_embeddings, dense_embeddings = self.prompt_encoder(
                points=points,
                boxes=image_record.get("boxes", None),
                masks=image_record.get("mask_inputs", None),
            )
            low_res_masks, iou_predictions = self.mask_decoder(
                image_embeddings=curr_embedding.unsqueeze(0),
                image_pe=self.prompt_encoder.get_dense_pe(),
                sparse_prompt_embeddings=sparse_embeddings,
                dense_prompt_embeddings=dense_embeddings,
                multimask_output=multimask_output,
            )
            masks = self.postprocess_masks(
                low_res_masks,
                input_size=image_record["image"].shape[-2:],
                original_size=image_record["original_size"],
            )
            masks = masks > self.mask_threshold
            outputs.append(
                {
                    "masks": masks,
                    "iou_predictions": iou_predictions,
                    "low_res_logits": low_res_masks,
                }
            )

        return outputs

    def postprocess_masks(
        self,
        masks: torch.Tensor,
        input_size: Tuple[int, ...],
        original_size: Tuple[int, ...],
    ) -> torch.Tensor:
        """
        Remove padding and upscale masks to the original image size.

        Arguments:
          masks (torch.Tensor): Batched masks from the mask_decoder,
            in BxCxHxW format.
          input_size (tuple(int, int)): The size of the image input to the
            model, in (H, W) format. Used to remove padding.
          original_size (tuple(int, int)): The original size of the image
            before resizing for input to the model, in (H, W) format.

        Returns:
          (torch.Tensor): Batched masks in BxCxHxW format, where (H, W)
            is given by original_size.
        """
        masks = F.interpolate(
            masks,
            (self.backbone.img_size, self.backbone.img_size),
            mode="bilinear",
            align_corners=False,
        )
        masks = masks[..., : input_size[0], : input_size[1]]
        masks = F.interpolate(
            masks, original_size, mode="bilinear", align_corners=False
        )
        return masks

    def preprocess(self, x: torch.Tensor) -> torch.Tensor:
        """Normalize pixel values and pad to a square input."""
        # Normalize colors
        x = (x - self.pixel_mean) / self.pixel_std

        # Pad
        h, w = x.shape[-2:]
        padh = self.backbone.img_size - h
        padw = self.backbone.img_size - w
        x = F.pad(x, (0, padw, 0, padh))
        return x