File size: 8,617 Bytes
2cfb891
290c238
 
d1c1a86
2cfb891
d1c1a86
 
5cfebb1
d1c1a86
 
2cfb891
8fa75cc
d1c1a86
290c238
 
216fbaf
 
2cfb891
 
216fbaf
290c238
d1c1a86
 
 
 
2cfb891
d1c1a86
 
 
 
 
 
 
2cfb891
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d1c1a86
 
 
 
 
 
290c238
d1c1a86
 
 
 
 
 
 
 
 
2cfb891
 
d1c1a86
 
290c238
d1c1a86
 
290c238
5cfebb1
290c238
d1c1a86
 
 
2cfb891
 
290c238
 
 
 
 
 
 
2cfb891
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
290c238
 
2cfb891
 
 
290c238
 
d1c1a86
 
216fbaf
290c238
d1c1a86
 
 
 
 
216fbaf
d1c1a86
2cfb891
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import json
import os

import gradio as gr
import numpy as np
import torch
import torch.nn.functional as F
from open_clip import create_model, get_tokenizer
from torchvision import transforms

import lib
from templates import openai_imagenet_template

hf_token = os.getenv("HF_TOKEN")

model_str = "hf-hub:imageomics/bioclip"
tokenizer_str = "ViT-B-16"
name_lookup_json = "name_lookup.json"
txt_emb_npy = "txt_emb.npy"

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

preprocess_img = transforms.Compose(
    [
        transforms.ToTensor(),
        transforms.Resize((224, 224), antialias=True),
        transforms.Normalize(
            mean=(0.48145466, 0.4578275, 0.40821073),
            std=(0.26862954, 0.26130258, 0.27577711),
        ),
    ]
)

ranks = ("Kingdom", "Phylum", "Class", "Order", "Family", "Genus", "Species")

open_domain_examples = [
    ["examples/Ursus-arctos.jpeg", "Species"],
    ["examples/Phoca-vitulina.png", "Species"],
    ["examples/Felis-catus.jpeg", "Genus"],
]
zero_shot_examples = [
    [
        "examples/Carnegiea-gigantea.png",
        "Carnegiea gigantea\nSchlumbergera opuntioides\nMammillaria albicoma",
    ],
    [
        "examples/Amanita-muscaria.jpeg",
        "Amanita fulva\nAmanita vaginata (grisette)\nAmanita calyptrata (coccoli)\nAmanita crocea\nAmanita rubescens (blusher)\nAmanita caesarea (Caesar's mushroom)\nAmanita jacksonii (American Caesar's mushroom)\nAmanita muscaria (fly agaric)\nAmanita pantherina (panther cap)",
    ],
    [
        "examples/Actinostola-abyssorum.png",
        "Animalia Cnidaria Hexacorallia Actiniaria Actinostolidae Actinostola abyssorum\nAnimalia Cnidaria Hexacorallia Actiniaria Actinostolidae Actinostola bulbosa\nAnimalia Cnidaria Hexacorallia Actiniaria Actinostolidae Actinostola callosa\nAnimalia Cnidaria Hexacorallia Actiniaria Actinostolidae Actinostola capensis\nAnimalia Cnidaria Hexacorallia Actiniaria Actinostolidae Actinostola carlgreni",
    ],
]


@torch.no_grad()
def get_txt_features(classnames, templates):
    all_features = []
    for classname in classnames:
        txts = [template(classname) for template in templates]
        txts = tokenizer(txts).to(device)
        txt_features = model.encode_text(txts)
        txt_features = F.normalize(txt_features, dim=-1).mean(dim=0)
        txt_features /= txt_features.norm()
        all_features.append(txt_features)
    all_features = torch.stack(all_features, dim=1)
    return all_features


@torch.no_grad()
def zero_shot_classification(img, cls_str: str) -> dict[str, float]:
    classes = [cls.strip() for cls in cls_str.split("\n") if cls.strip()]
    txt_features = get_txt_features(classes, openai_imagenet_template)

    img = preprocess_img(img).to(device)
    img_features = model.encode_image(img.unsqueeze(0))
    img_features = F.normalize(img_features, dim=-1)

    logits = (model.logit_scale.exp() * img_features @ txt_features).squeeze()
    probs = F.softmax(logits, dim=0).to("cpu").tolist()
    return {cls: prob for cls, prob in zip(classes, probs)}


@torch.no_grad()
def open_domain_classification(img, rank: int) -> list[dict[str, float]]:
    """
    Predicts from the top of the tree of life down to the species.
    """
    img = preprocess_img(img).to(device)
    img_features = model.encode_image(img.unsqueeze(0))
    img_features = F.normalize(img_features, dim=-1)

    outputs = []

    name = []
    for _ in range(rank + 1):
        children = tuple(zip(*name_lookup.children(name)))
        if not children:
            break
        values, indices = children
        txt_features = txt_emb[:, indices].to(device)
        logits = (model.logit_scale.exp() * img_features @ txt_features).view(-1)

        probs = F.softmax(logits, dim=0).to("cpu").tolist()
        parent = " ".join(name)
        outputs.append(
            {f"{parent} {value}": prob for value, prob in zip(values, probs)}
        )

        top = values[logits.argmax()]
        name.append(top)

    while len(outputs) < 7:
        outputs.append({})

    return list(reversed(outputs))


def change_output(choice):
    return [
        gr.Label(
            num_top_classes=5, label=rank, show_label=True, visible=(6 - i <= choice)
        )
        for i, rank in enumerate(reversed(ranks))
    ]


def get_name_lookup(path):
    with open(path) as fd:
        return lib.TaxonomicTree.from_dict(json.load(fd))


if __name__ == "__main__":
    print("Starting.")
    model = create_model(model_str, output_dict=True, require_pretrained=True)
    model = model.to(device)
    print("Created model.")

    model = torch.compile(model)
    print("Compiled model.")

    tokenizer = get_tokenizer(tokenizer_str)

    name_lookup = get_name_lookup(name_lookup_json)
    txt_emb = torch.from_numpy(np.load(txt_emb_npy, mmap_mode="r"))

    done = txt_emb.any(axis=0).sum().item()
    total = txt_emb.shape[1]
    status_msg = ""
    if done != total:
        status_msg = f"{done}/{total} ({done / total * 100:.1f}%) indexed"

    with gr.Blocks() as app:
        img_input = gr.Image()

        with gr.Tab("Open-Ended"):
            with gr.Row():
                with gr.Column():
                    rank_dropdown = gr.Dropdown(
                        label="Taxonomic Rank",
                        info="Which taxonomic rank to predict. Fine-grained ranks (genus, species) are more challenging.",
                        choices=ranks,
                        value="Species",
                        type="index",
                    )
                    open_domain_btn = gr.Button("Submit", variant="primary")
                    gr.Examples(
                        examples=open_domain_examples,
                        inputs=[img_input, rank_dropdown],
                    )

                with gr.Column():
                    open_domain_outputs = [
                        gr.Label(num_top_classes=5, label=rank, show_label=True)
                        for rank in reversed(ranks)
                    ]
                    open_domain_flag_btn = gr.Button("Flag Mistake", variant="primary")

            open_domain_callback = gr.HuggingFaceDatasetSaver(
                hf_token, "imageomics/bioclip-demo-open-domain-mistakes", private=True
            )
            open_domain_callback.setup(
                [img_input, *open_domain_outputs], flagging_dir="logs/flagged"
            )
            open_domain_flag_btn.click(
                lambda *args: open_domain_callback.flag(args),
                [img_input, *open_domain_outputs],
                None,
                preprocess=False,
            )

        with gr.Tab("Zero-Shot"):
            with gr.Row():
                with gr.Column():
                    classes_txt = gr.Textbox(
                        placeholder="Canis familiaris (dog)\nFelis catus (cat)\n...",
                        lines=3,
                        label="Classes",
                        show_label=True,
                        info="Use taxonomic names where possible; include common names if possible.",
                    )
                    zero_shot_btn = gr.Button("Submit", variant="primary")
                    gr.Examples(
                        examples=zero_shot_examples,
                        inputs=[img_input, classes_txt],
                    )

                with gr.Column():
                    zero_shot_output = gr.Label(
                        num_top_classes=5, label="Prediction", show_label=True
                    )
                    zero_shot_flag_btn = gr.Button("Flag Mistake", variant="primary")

            zero_shot_callback = gr.HuggingFaceDatasetSaver(
                hf_token, "imageomics/bioclip-demo-zero-shot-mistakes", private=True
            )
            zero_shot_callback.setup(
                [img_input, zero_shot_output], flagging_dir="logs/flagged"
            )
            zero_shot_flag_btn.click(
                lambda *args: zero_shot_callback.flag(args),
                [img_input, zero_shot_output],
                None,
                preprocess=False,
            )

        rank_dropdown.change(
            fn=change_output, inputs=rank_dropdown, outputs=open_domain_outputs
        )

        open_domain_btn.click(
            fn=open_domain_classification,
            inputs=[img_input, rank_dropdown],
            outputs=open_domain_outputs,
        )

        zero_shot_btn.click(
            fn=zero_shot_classification,
            inputs=[img_input, classes_txt],
            outputs=zero_shot_output,
        )

    app.queue(max_size=20)
    app.launch()