File size: 1,396 Bytes
50c5146
 
 
5af8e1d
 
 
 
 
 
c583569
 
 
 
5af8e1d
c583569
 
 
 
 
 
 
6586dd5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c583569
 
 
 
 
5af8e1d
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
---
license: mit
---

Model convert from [https://github.com/KichangKim/DeepDanbooru](https://github.com/KichangKim/DeepDanbooru)

Usage:

```python
import cv2
import numpy as np
import onnxruntime as rt
from huggingface_hub import hf_hub_download

tagger_model_path = hf_hub_download(repo_id="skytnt/deepdanbooru_onnx", filename="deepdanbooru.onnx")

tagger_model = rt.InferenceSession(tagger_model_path, providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
tagger_model_meta = tagger_model.get_modelmeta().custom_metadata_map
tagger_tags = eval(tagger_model_meta['tags'])

def tagger_predict(image, score_threshold):
    s = 512
    h, w = image.shape[:-1]
    h, w = (s, int(s * w / h)) if h > w else (int(s * h / w), s)
    ph, pw = s - h, s - w
    image = cv2.resize(image, (w, h), interpolation=cv2.INTER_AREA)
    image = cv2.copyMakeBorder(image, ph // 2, ph - ph // 2, pw // 2, pw - pw // 2, cv2.BORDER_REPLICATE)
    image = image.astype(np.float32) / 255
    image = img_new[np.newaxis, :]
    probs = tagger_model.run(None, {"input_1": image})[0][0]
    probs = probs.astype(np.float32)
    res = []
    for prob, label in zip(probs.tolist(), tagger_tags):
        if prob < score_threshold:
            continue
        res.append(label)
    return res

img = cv2.imread("test.jpg")
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
tags = tagger_predict(img, 0.5)
print(tags)
```