File size: 9,267 Bytes
50704de
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
271
272
273
274
275
276
277
278
from typing import Any
import argparse
import pathlib

import torch
from torch import nn
from sam2.build_sam import build_sam2
from sam2.modeling.sam2_base import SAM2Base


class SAM2ImageEncoder(nn.Module):
    def __init__(self, sam_model: SAM2Base) -> None:
        super().__init__()
        self.model = sam_model
        self.image_encoder = sam_model.image_encoder
        self.no_mem_embed = sam_model.no_mem_embed

    def forward(self, x: torch.Tensor) -> tuple[Any, Any, Any]:
        backbone_out = self.image_encoder(x)
        backbone_out["backbone_fpn"][0] = self.model.sam_mask_decoder.conv_s0(
            backbone_out["backbone_fpn"][0]
        )
        backbone_out["backbone_fpn"][1] = self.model.sam_mask_decoder.conv_s1(
            backbone_out["backbone_fpn"][1]
        )

        feature_maps = backbone_out["backbone_fpn"][
            -self.model.num_feature_levels :
        ]
        vision_pos_embeds = backbone_out["vision_pos_enc"][
            -self.model.num_feature_levels :
        ]

        feat_sizes = [(x.shape[-2], x.shape[-1]) for x in vision_pos_embeds]

        # flatten NxCxHxW to HWxNxC
        vision_feats = [x.flatten(2).permute(2, 0, 1) for x in feature_maps]
        vision_feats[-1] = vision_feats[-1] + self.no_mem_embed

        feats = [
            feat.permute(1, 2, 0).reshape(1, -1, *feat_size)
            for feat, feat_size in zip(vision_feats[::-1], feat_sizes[::-1])
        ][::-1]

        return feats[0], feats[1], feats[2]


class SAM2ImageDecoder(nn.Module):
    def __init__(self, sam_model: SAM2Base, multimask_output: bool) -> None:
        super().__init__()
        self.mask_decoder = sam_model.sam_mask_decoder
        self.prompt_encoder = sam_model.sam_prompt_encoder
        self.model = sam_model
        self.img_size = sam_model.image_size
        self.multimask_output = multimask_output

    @torch.no_grad()
    def forward(
        self,
        image_embed: torch.Tensor,
        high_res_feats_0: torch.Tensor,
        high_res_feats_1: torch.Tensor,
        point_coords: torch.Tensor,
        point_labels: torch.Tensor,
        orig_im_size: torch.Tensor,
        mask_input: torch.Tensor,
        has_mask_input: torch.Tensor,
    ):
        sparse_embedding = self._embed_points(point_coords, point_labels)
        self.sparse_embedding = sparse_embedding
        dense_embedding = self._embed_masks(mask_input, has_mask_input)

        high_res_feats = [high_res_feats_0, high_res_feats_1]
        image_embed = image_embed

        masks, iou_predictions, _, _ = self.mask_decoder.predict_masks(
            image_embeddings=image_embed,
            image_pe=self.prompt_encoder.get_dense_pe(),
            sparse_prompt_embeddings=sparse_embedding,
            dense_prompt_embeddings=dense_embedding,
            repeat_image=False,
            high_res_features=high_res_feats,
        )

        if self.multimask_output:
            masks = masks[:, 1:, :, :]
            iou_predictions = iou_predictions[:, 1:]
        else:
            masks, iou_predictions = (
                self.mask_decoder._dynamic_multimask_via_stability(
                    masks, iou_predictions
                )
            )

        masks = torch.clamp(masks, -32.0, 32.0)

        return masks, iou_predictions

    def _embed_points(
        self, point_coords: torch.Tensor, point_labels: torch.Tensor
    ) -> torch.Tensor:

        point_coords = point_coords + 0.5

        padding_point = torch.zeros(
            (point_coords.shape[0], 1, 2), device=point_coords.device
        )
        padding_label = -torch.ones(
            (point_labels.shape[0], 1), device=point_labels.device
        )
        point_coords = torch.cat([point_coords, padding_point], dim=1)
        point_labels = torch.cat([point_labels, padding_label], dim=1)

        point_coords[:, :, 0] = point_coords[:, :, 0] / self.model.image_size
        point_coords[:, :, 1] = point_coords[:, :, 1] / self.model.image_size

        point_embedding = self.prompt_encoder.pe_layer._pe_encoding(
            point_coords
        )
        point_labels = point_labels.unsqueeze(-1).expand_as(point_embedding)

        point_embedding = point_embedding * (point_labels != -1)
        point_embedding = (
            point_embedding
            + self.prompt_encoder.not_a_point_embed.weight
            * (point_labels == -1)
        )

        for i in range(self.prompt_encoder.num_point_embeddings):
            point_embedding = (
                point_embedding
                + self.prompt_encoder.point_embeddings[i].weight
                * (point_labels == i)
            )

        return point_embedding

    def _embed_masks(
        self, input_mask: torch.Tensor, has_mask_input: torch.Tensor
    ) -> torch.Tensor:
        mask_embedding = has_mask_input * self.prompt_encoder.mask_downscaling(
            input_mask
        )
        mask_embedding = mask_embedding + (
            1 - has_mask_input
        ) * self.prompt_encoder.no_mask_embed.weight.reshape(1, -1, 1, 1)
        return mask_embedding


if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description="Export the SAM2 prompt encoder and mask decoder to an ONNX model."
    )
    parser.add_argument(
        "--checkpoint",
        type=str,
        required=True,
        help="The path to the SAM model checkpoint.",
    )

    parser.add_argument(
        "--output_encoder",
        type=str,
        required=True,
        help="The filename to save the encoder ONNX model to.",
    )

    parser.add_argument(
        "--output_decoder",
        type=str,
        required=True,
        help="The filename to save the decoder ONNX model to.",
    )

    parser.add_argument(
        "--model_type",
        type=str,
        required=True,
        help="In the form of sam2_hiera_{tiny, small, base_plus, large}.",
    )

    parser.add_argument(
        "--opset",
        type=int,
        default=17,
        help="The ONNX opset version to use. Must be >=11",
    )

    args = parser.parse_args()

    input_size = (1024, 1024)
    multimask_output = False
    model_type = args.model_type
    if model_type == "sam2.1_hiera_tiny":
        model_cfg = "configs/sam2.1/sam2.1_hiera_t.yaml"
    elif model_type == "sam2.1_hiera_small":
        model_cfg = "configs/sam2.1/sam2.1_hiera_s.yaml"
    elif model_type == "sam2.1_hiera_base_plus":
        model_cfg = "configs/sam2.1/sam2.1_hiera_b+.yaml"
    elif model_type == "sam2.1_hiera_large":
        model_cfg = "configs/sam2.1/sam2.1_hiera_l.yaml"
    else:
        model_cfg = "configs/sam2.1/sam2.1_hiera_l.yaml"

    sam2_model = build_sam2(model_cfg, args.checkpoint, device="cpu")
    img = torch.randn(1, 3, input_size[0], input_size[1]).cpu()
    sam2_encoder = SAM2ImageEncoder(sam2_model).cpu()
    high_res_feats_0, high_res_feats_1, image_embed = sam2_encoder(img)

    pathlib.Path(args.output_encoder).parent.mkdir(parents=True, exist_ok=True)
    torch.onnx.export(
        sam2_encoder,
        img,
        args.output_encoder,
        export_params=True,
        opset_version=args.opset,
        do_constant_folding=True,
        input_names=["image"],
        output_names=["high_res_feats_0", "high_res_feats_1", "image_embed"],
    )
    print("Saved encoder to", args.output_encoder)

    sam2_decoder = SAM2ImageDecoder(
        sam2_model, multimask_output=multimask_output
    ).cpu()

    embed_dim = sam2_model.sam_prompt_encoder.embed_dim
    embed_size = (
        sam2_model.image_size // sam2_model.backbone_stride,
        sam2_model.image_size // sam2_model.backbone_stride,
    )
    mask_input_size = [4 * x for x in embed_size]
    print(embed_dim, embed_size, mask_input_size)

    point_coords = torch.randint(
        low=0, high=input_size[1], size=(1, 5, 2), dtype=torch.float
    )
    point_labels = torch.randint(low=0, high=1, size=(1, 5), dtype=torch.float)
    mask_input = torch.randn(1, 1, *mask_input_size, dtype=torch.float)
    has_mask_input = torch.tensor([1], dtype=torch.float)
    orig_im_size = torch.tensor([input_size[0], input_size[1]], dtype=torch.int)

    pathlib.Path(args.output_decoder).parent.mkdir(parents=True, exist_ok=True)
    torch.onnx.export(
        sam2_decoder,
        (
            image_embed,
            high_res_feats_0,
            high_res_feats_1,
            point_coords,
            point_labels,
            orig_im_size,
            mask_input,
            has_mask_input,
        ),
        args.output_decoder,
        export_params=True,
        opset_version=args.opset,
        do_constant_folding=True,
        input_names=[
            "image_embed",
            "high_res_feats_0",
            "high_res_feats_1",
            "point_coords",
            "point_labels",
            "orig_im_size",
            "mask_input",
            "has_mask_input",
        ],
        output_names=["masks", "iou_predictions"],
        dynamic_axes={
            "point_coords": {0: "num_labels", 1: "num_points"},
            "point_labels": {0: "num_labels", 1: "num_points"},
            "mask_input": {0: "num_labels"},
            "has_mask_input": {0: "num_labels"},
        },
    )
    print("Saved decoder to", args.output_decoder)