File size: 1,480 Bytes
3ae84a3
 
 
 
78cdedf
3ae84a3
 
 
 
 
0d69242
9b28e54
3ae84a3
 
0d69242
 
3ae84a3
 
0d69242
78cdedf
3ae84a3
 
0d69242
9b28e54
 
78cdedf
0d69242
c45624f
 
8fd2365
 
 
3ae84a3
 
22ac4b7
8fd2365
 
3ae84a3
 
 
0d69242
 
3ae84a3
 
8fd2365
3ae84a3
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
import pickle

import gradio as gr
from datasets import load_dataset
from transformers import AutoModel, AutoFeatureExtractor


seed = 42

# Only runs once when the script is first run.
with open("index_768.pickle", "rb") as handle:
    index = pickle.load(handle)

# Load model for computing embeddings.
feature_extractor = AutoFeatureExtractor.from_pretrained("sasha/autotrain-butterfly-similarity-2490576840")
model = AutoModel.from_pretrained("sasha/autotrain-butterfly-similarity-2490576840")

# Candidate images.
dataset = load_dataset("sasha/butterflies_10k_names_multiple")
ds = dataset["train"]


def query(image, top_k=4):
    inputs = feature_extractor(image, return_tensors="pt")
    model_output = model(**inputs)
    embedding = model_output.pooler_output.detach()
    results = index.query(embedding, k=top_k)
    inx = results[0][0].tolist()
    images = ds.select(inx)["image"]
    captions = ds.select(inx)["name"]
    images_with_captions = [(i, c) for i, c in zip(images,captions)]
    return images_with_captions


title = "Find my Butterfly 🦋"
description = "Use this Space to find your butterfly, based on the [iNaturalist butterfly dataset](https://huggingface.co/datasets/huggan/inat_butterflies_top10k)!"


gr.Interface(
    query,
    inputs=[gr.Image(type="pil")],
    outputs=gr.Gallery().style(grid=[2], height="auto"),
    title=title,
    description=description,
    examples=[["elton.jpg"],["ken.jpg"],["gaga.jpg"],["taylor.jpg"]],
).launch()