File size: 11,661 Bytes
3dac99f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.

# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.

import numpy as np
import torch

from segment_anything.modeling import Sam

from typing import Optional, Tuple

from .utils.transforms import ResizeLongestSide


class SamPredictor:
    def __init__(
        self,
        sam_model: Sam,
    ) -> None:
        """
        Uses SAM to calculate the image embedding for an image, and then
        allow repeated, efficient mask prediction given prompts.

        Arguments:
          sam_model (Sam): The model to use for mask prediction.
        """
        super().__init__()
        self.model = sam_model
        self.transform = ResizeLongestSide(sam_model.image_encoder.img_size)
        self.reset_image()

    def set_image(
        self,
        image: np.ndarray,
        image_format: str = "BGR",
    ) -> None:
        """
        Calculates the image embeddings for the provided image, allowing
        masks to be predicted with the 'predict' method.

        Arguments:
          image (np.ndarray): The image for calculating masks. Expects an
            image in HWC uint8 format, with pixel values in [0, 255].
          image_format (str): The color format of the image, in ['RGB', 'BGR'].
        """
        assert image_format in [
            "RGB",
            "BGR",
        ], f"image_format must be in ['RGB', 'BGR'], is {image_format}."
        if image_format != self.model.image_format:
            image = image[..., ::-1]

        # Transform the image to the form expected by the model
        input_image = self.transform.apply_image(image)
        input_image_torch = torch.as_tensor(input_image, device=self.device)
        input_image_torch = input_image_torch.permute(2, 0, 1).contiguous()[None, :, :, :]

        self.set_torch_image(input_image_torch, image.shape[:2])

    @torch.no_grad()
    def set_torch_image(
        self,
        transformed_image: torch.Tensor,
        original_image_size: Tuple[int, ...],
    ) -> None:
        """
        Calculates the image embeddings for the provided image, allowing
        masks to be predicted with the 'predict' method. Expects the input
        image to be already transformed to the format expected by the model.

        Arguments:
          transformed_image (torch.Tensor): The input image, with shape
            1x3xHxW, which has been transformed with ResizeLongestSide.
          original_image_size (tuple(int, int)): The size of the image
            before transformation, in (H, W) format.
        """
        assert (
            len(transformed_image.shape) == 4
            and transformed_image.shape[1] == 3
            and max(*transformed_image.shape[2:]) == self.model.image_encoder.img_size
        ), f"set_torch_image input must be BCHW with long side {self.model.image_encoder.img_size}."
        self.reset_image()

        self.original_size = original_image_size
        self.input_size = tuple(transformed_image.shape[-2:])
        input_image = self.model.preprocess(transformed_image)
        self.features = self.model.image_encoder.forward_ori(input_image)
        self.is_image_set = True

    def predict(
        self,
        point_coords: Optional[np.ndarray] = None,
        point_labels: Optional[np.ndarray] = None,
        box: Optional[np.ndarray] = None,
        mask_input: Optional[np.ndarray] = None,
        multimask_output: bool = True,
        return_logits: bool = False,
    ) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
        """
        Predict masks for the given input prompts, using the currently set image.

        Arguments:
          point_coords (np.ndarray or None): A Nx2 array of point prompts to the
            model. Each point is in (X,Y) in pixels.
          point_labels (np.ndarray or None): A length N array of labels for the
            point prompts. 1 indicates a foreground point and 0 indicates a
            background point.
          box (np.ndarray or None): A length 4 array given a box prompt to the
            model, in XYXY format.
          mask_input (np.ndarray): A low resolution mask input to the model, typically
            coming from a previous prediction iteration. Has form 1xHxW, where
            for SAM, H=W=256.
          multimask_output (bool): If true, the model will return three masks.
            For ambiguous input prompts (such as a single click), this will often
            produce better masks than a single prediction. If only a single
            mask is needed, the model's predicted quality score can be used
            to select the best mask. For non-ambiguous prompts, such as multiple
            input prompts, multimask_output=False can give better results.
          return_logits (bool): If true, returns un-thresholded masks logits
            instead of a binary mask.

        Returns:
          (np.ndarray): The output masks in CxHxW format, where C is the
            number of masks, and (H, W) is the original image size.
          (np.ndarray): An array of length C containing the model's
            predictions for the quality of each mask.
          (np.ndarray): An array of shape CxHxW, where C is the number
            of masks and H=W=256. These low resolution logits can be passed to
            a subsequent iteration as mask input.
        """
        if not self.is_image_set:
            raise RuntimeError("An image must be set with .set_image(...) before mask prediction.")

        # Transform input prompts
        coords_torch, labels_torch, box_torch, mask_input_torch = None, None, None, None
        if point_coords is not None:
            assert (
                point_labels is not None
            ), "point_labels must be supplied if point_coords is supplied."
            point_coords = self.transform.apply_coords(point_coords, self.original_size)
            coords_torch = torch.as_tensor(point_coords, dtype=torch.float, device=self.device)
            labels_torch = torch.as_tensor(point_labels, dtype=torch.int, device=self.device)
            coords_torch, labels_torch = coords_torch[None, :, :], labels_torch[None, :]
        if box is not None:
            box = self.transform.apply_boxes(box, self.original_size)
            box_torch = torch.as_tensor(box, dtype=torch.float, device=self.device)
            box_torch = box_torch[None, :]
        if mask_input is not None:
            mask_input_torch = torch.as_tensor(mask_input, dtype=torch.float, device=self.device)
            mask_input_torch = mask_input_torch[None, :, :, :]

        masks, iou_predictions, low_res_masks = self.predict_torch(
            coords_torch,
            labels_torch,
            box_torch,
            mask_input_torch,
            multimask_output,
            return_logits=return_logits,
        )

        masks_np = masks[0].detach().cpu().numpy()
        iou_predictions_np = iou_predictions[0].detach().cpu().numpy()
        low_res_masks_np = low_res_masks[0].detach().cpu().numpy()
        return masks_np, iou_predictions_np, low_res_masks_np

    @torch.no_grad()
    def predict_torch(
        self,
        point_coords: Optional[torch.Tensor],
        point_labels: Optional[torch.Tensor],
        boxes: Optional[torch.Tensor] = None,
        mask_input: Optional[torch.Tensor] = None,
        multimask_output: bool = True,
        return_logits: bool = False,
    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
        """
        Predict masks for the given input prompts, using the currently set image.
        Input prompts are batched torch tensors and are expected to already be
        transformed to the input frame using ResizeLongestSide.

        Arguments:
          point_coords (torch.Tensor or None): A BxNx2 array of point prompts to the
            model. Each point is in (X,Y) in pixels.
          point_labels (torch.Tensor or None): A BxN array of labels for the
            point prompts. 1 indicates a foreground point and 0 indicates a
            background point.
          boxes (np.ndarray or None): A Bx4 array given a box prompt to the
            model, in XYXY format.
          mask_input (np.ndarray): A low resolution mask input to the model, typically
            coming from a previous prediction iteration. Has form Bx1xHxW, where
            for SAM, H=W=256. Masks returned by a previous iteration of the
            predict method do not need further transformation.
          multimask_output (bool): If true, the model will return three masks.
            For ambiguous input prompts (such as a single click), this will often
            produce better masks than a single prediction. If only a single
            mask is needed, the model's predicted quality score can be used
            to select the best mask. For non-ambiguous prompts, such as multiple
            input prompts, multimask_output=False can give better results.
          return_logits (bool): If true, returns un-thresholded masks logits
            instead of a binary mask.

        Returns:
          (torch.Tensor): The output masks in BxCxHxW format, where C is the
            number of masks, and (H, W) is the original image size.
          (torch.Tensor): An array of shape BxC containing the model's
            predictions for the quality of each mask.
          (torch.Tensor): An array of shape BxCxHxW, where C is the number
            of masks and H=W=256. These low res logits can be passed to
            a subsequent iteration as mask input.
        """
        if not self.is_image_set:
            raise RuntimeError("An image must be set with .set_image(...) before mask prediction.")

        if point_coords is not None:
            points = (point_coords, point_labels)
        else:
            points = None

        # Embed prompts
        sparse_embeddings, dense_embeddings = self.model.prompt_encoder(
            points=points,
            boxes=boxes,
            masks=mask_input,
        )

        # Predict masks
        low_res_masks, iou_predictions = self.model.mask_decoder(
            image_embeddings=self.features,
            image_pe=self.model.prompt_encoder.get_dense_pe(),
            sparse_prompt_embeddings=sparse_embeddings,
            dense_prompt_embeddings=dense_embeddings,
            multimask_output=multimask_output,
        )

        # Upscale the masks to the original image resolution
        masks = self.model.postprocess_masks(low_res_masks, self.input_size, self.original_size)

        if not return_logits:
            masks = masks > self.model.mask_threshold

        return masks, iou_predictions, low_res_masks

    def get_image_embedding(self) -> torch.Tensor:
        """
        Returns the image embeddings for the currently set image, with
        shape 1xCxHxW, where C is the embedding dimension and (H,W) are
        the embedding spatial dimension of SAM (typically C=256, H=W=64).
        """
        if not self.is_image_set:
            raise RuntimeError(
                "An image must be set with .set_image(...) to generate an embedding."
            )
        assert self.features is not None, "Features must exist if an image has been set."
        return self.features

    @property
    def device(self) -> torch.device:
        return self.model.device

    def reset_image(self) -> None:
        """Resets the currently set image."""
        self.is_image_set = False
        self.features = None
        self.orig_h = None
        self.orig_w = None
        self.input_h = None
        self.input_w = None