File size: 7,898 Bytes
fac52b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from typing import List, Union

import numpy as np
import torch
from diffusers.modular_pipelines import (
    ComponentSpec,
    InputParam,
    ModularPipelineBlocks,
    OutputParam,
    PipelineState,
)
from PIL import Image, ImageDraw
from transformers import Florence2ForConditionalGeneration, AutoProcessor


class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
    @property
    def expected_components(self):
        return [
            ComponentSpec(
                name="image_annotator",
                type_hint=Florence2ForConditionalGeneration,
                repo="florence-community/Florence-2-base-ft",
            ),
            ComponentSpec(
                name="image_annotator_processor",
                type_hint=AutoProcessor,
                repo="florence-community/Florence-2-base-ft",
            ),
        ]

    @property
    def inputs(self) -> List[InputParam]:
        return [
            InputParam(
                "image",
                type_hint=Union[Image.Image, List[Image.Image]],
                required=True,
                description="Image(s) to annotate",
            ),
            InputParam(
                "annotation_task",
                type_hint=Union[str, List[str]],
                required=True,
                default="<REFERRING_EXPRESSION_SEGMENTATION>",
                description="""Annotation Task to perform on the image.
                Supported Tasks:

                <OD>
                <REFERRING_EXPRESSION_SEGMENTATION>
                <CAPTION>
                <DETAILED_CAPTION>
                <MORE_DETAILED_CAPTION>
                <DENSE_REGION_CAPTION>
                <CAPTION_TO_PHRASE_GROUNDING>
                <OPEN_VOCABULARY_DETECTION>

                """,
            ),
            InputParam(
                "annotation_prompt",
                type_hint=Union[str, List[str]],
                required=True,
                description="""Annotation Prompt to provide more context to the task.
                Can be used to detect or segment out specific elements in the image
                """,
            ),
            InputParam(
                "annotation_output_type",
                type_hint=str,
                required=True,
                default="mask_image",
                description="""Output type from annotation predictions. Availabe options are
                annotation:
                    - raw annotation predictions from the model based on task type.
                mask_image:
                    -black and white mask image for the given image based on the task type
                mask_overlay:
                    - white mask overlayed on the original image
                bounding_box:
                    - bounding boxes drawn on the original image
                """,
            ),
            InputParam(
                "annotation_overlay",
                type_hint=bool,
                required=True,
                default=False,
                description="",
            ),
            InputParam(
                "fill",
                type_hint=str,
                default="white",
                description="",
            ),
        ]

    @property
    def intermediate_outputs(self) -> List[OutputParam]:
        return [
            OutputParam(
                "mask_image",
                type_hint=Image,
                description="Inpainting Mask for input Image(s)",
            ),
            OutputParam(
                "annotations",
                type_hint=dict,
                description="Annotations Predictions for input Image(s)",
            ),
            OutputParam(
                "image",
                type_hint=Image,
                description="Annotated input Image(s)",
            ),
        ]

    def get_annotations(self, components, images, prompts, task):
        task_prompts = [task + prompt for prompt in prompts]

        inputs = components.image_annotator_processor(
            text=task_prompts, images=images, return_tensors="pt"
        ).to(components.image_annotator.device, components.image_annotator.dtype)

        generated_ids = components.image_annotator.generate(
            input_ids=inputs["input_ids"],
            pixel_values=inputs["pixel_values"],
            max_new_tokens=1024,
            early_stopping=False,
            do_sample=False,
            num_beams=3,
        )
        annotations = components.image_annotator_processor.batch_decode(
            generated_ids, skip_special_tokens=False
        )
        outputs = []
        for image, annotation in zip(images, annotations):
            outputs.append(
                components.image_annotator_processor.post_process_generation(
                    annotation, task=task, image_size=(image.width, image.height)
                )
            )
        return outputs

    def prepare_mask(self, images, annotations, overlay=False, fill="white"):
        masks = []
        for image, annotation in zip(images, annotations):
            mask_image = image.copy() if overlay else Image.new("L", image.size, 0)
            draw = ImageDraw.Draw(mask_image)

            for _, _annotation in annotation.items():
                if "polygons" in _annotation:
                    for polygon in _annotation["polygons"]:
                        polygon = np.array(polygon).reshape(-1, 2)
                        if len(polygon) < 3:
                            continue
                        polygon = polygon.reshape(-1).tolist()
                        draw.polygon(polygon, fill=fill)

                elif "bbox" in _annotation:
                    bbox = _annotation["bbox"]
                    draw.rectangle(bbox, fill="white")

            masks.append(mask_image)

        return masks

    def prepare_bounding_boxes(self, images, annotations):
        outputs = []
        for image, annotation in zip(images, annotations):
            image_copy = image.copy()
            draw = ImageDraw.Draw(image_copy)
            for _, _annotation in annotation.items():
                bbox = _annotation["bbox"]
                label = _annotation["label"]

                draw.rectangle(bbox, outline="red", width=3)
                draw.text((bbox[0], bbox[1] - 20), label, fill="red")

            outputs.append(image_copy)

        return outputs

    def prepare_inputs(self, images, prompts):
        prompts = prompts or ""

        if isinstance(images, Image.Image):
            images = [images]
        if isinstance(prompts, str):
            prompts = [prompts]

        if len(images) != len(prompts):
            raise ValueError("Number of images and annotation prompts must match.")

        return images, prompts

    @torch.no_grad()
    def __call__(self, components, state: PipelineState) -> PipelineState:
        block_state = self.get_block_state(state)
        images, annotation_task_prompt = self.prepare_inputs(
            block_state.image, block_state.annotation_prompt
        )
        task = block_state.annotation_task
        fill = block_state.fill

        annotations = self.get_annotations(
            components, images, annotation_task_prompt, task
        )
        block_state.annotations = annotations
        if block_state.annotation_output_type == "mask_image":
            block_state.mask_image = self.prepare_mask(images, annotations)
        else:
            block_state.mask_image = None

        if block_state.annotation_output_type == "mask_overlay":
            block_state.image = self.prepare_mask(
                images, annotations, overlay=True, fill=fill
            )

        elif block_state.annotation_output_type == "bounding_box":
            block_state.image = self.prepare_bounding_boxes(images, annotations)

        self.set_block_state(state, block_state)

        return components, state