---
tags:
- image-classification
- timm
- transformers
- animetimm
- dghs-imgutils
library_name: timm
license: gpl-3.0
datasets:
- animetimm/danbooru-wdtagger-v4-w640-ws-full
base_model:
- timm/caformer_m36.sail_in22k_ft_in1k_384
---

# Anime Tagger caformer_m36.dbv4-full

## Model Details

- **Model Type:** Multilabel Image classification / feature backbone
- **Model Stats:**
  - Params: 82.7M
  - FLOPs / MACs: 74.9G / 37.3G
  - Image size: train = 384 x 384, test = 384 x 384
- **Dataset:** [animetimm/danbooru-wdtagger-v4-w640-ws-full](https://huggingface.co/datasets/animetimm/danbooru-wdtagger-v4-w640-ws-full)
  - Tags Count: 12476
    - General (#0) Tags Count: 9225
    - Character (#4) Tags Count: 3247
    - Rating (#9) Tags Count: 4

## Results

|     #      |    Macro@0.40 (F1/MCC/P/R)    |    Micro@0.40 (F1/MCC/P/R)    |  Macro@Best (F1/P/R)  |
|:----------:|:-----------------------------:|:-----------------------------:|:---------------------:|
| Validation | 0.514 / 0.524 / 0.601 / 0.477 | 0.676 / 0.675 / 0.689 / 0.662 |          ---          |
|    Test    | 0.515 / 0.525 / 0.602 / 0.478 | 0.676 / 0.675 / 0.690 / 0.663 | 0.559 / 0.569 / 0.573 |

* `Macro/Micro@0.40` means the metrics on the threshold 0.40.
* `Macro@Best` means the mean metrics on the tag-level thresholds on each tags, which should have the best F1 scores.

## Thresholds

|  Category  |   Name    |  Alpha  |  Threshold  |  Micro@Thr (F1/P/R)   |  Macro@0.40 (F1/P/R)  |  Macro@Best (F1/P/R)  |
|:----------:|:---------:|:-------:|:-----------:|:---------------------:|:---------------------:|:---------------------:|
|     0      |  general  |    1    |    0.37     | 0.664 / 0.661 / 0.667 | 0.383 / 0.488 / 0.343 | 0.436 / 0.439 / 0.463 |
|     4      | character |    1    |    0.45     | 0.916 / 0.944 / 0.889 | 0.889 / 0.925 / 0.861 | 0.907 / 0.936 / 0.884 |
|     9      |  rating   |    1    |     0.4     | 0.821 / 0.782 / 0.863 | 0.829 / 0.800 / 0.861 | 0.830 / 0.808 / 0.856 |

* `Micro@Thr` means the metrics on the category-level suggested thresholds, which are listed in the table above.
* `Macro@0.40` means the metrics on the threshold 0.40.
* `Macro@Best` means the metrics on the tag-level thresholds on each tags, which should have the best F1 scores.

For tag-level thresholds, you can find them in [selected_tags.csv](https://huggingface.co/animetimm/caformer_m36.dbv4-full/resolve/main/selected_tags.csv).

## How to Use

We provided a sample image for our code samples, you can find it [here](https://huggingface.co/animetimm/caformer_m36.dbv4-full/blob/main/sample.webp).

### Use TIMM And Torch

Install [dghs-imgutils](https://github.com/deepghs/imgutils), [timm](https://github.com/huggingface/pytorch-image-models) and other necessary requirements with the following command

```shell
pip install 'dghs-imgutils>=0.17.0' torch huggingface_hub timm pillow pandas
```

After that you can load this model with timm library, and use it for train, validation and test, with the following code

```python
import json

import pandas as pd
import torch
from huggingface_hub import hf_hub_download
from imgutils.data import load_image
from imgutils.preprocess import create_torchvision_transforms
from timm import create_model

repo_id = 'animetimm/caformer_m36.dbv4-full'
model = create_model(f'hf-hub:{repo_id}', pretrained=True)
model.eval()

with open(hf_hub_download(repo_id=repo_id, repo_type='model', filename='preprocess.json'), 'r') as f:
    preprocessor = create_torchvision_transforms(json.load(f)['test'])
# Compose(
#     PadToSize(size=(512, 512), interpolation=bilinear, background_color=white)
#     Resize(size=384, interpolation=bicubic, max_size=None, antialias=True)
#     CenterCrop(size=[384, 384])
#     MaybeToTensor()
#     Normalize(mean=tensor([0.4850, 0.4560, 0.4060]), std=tensor([0.2290, 0.2240, 0.2250]))
# )

image = load_image('https://huggingface.co/animetimm/caformer_m36.dbv4-full/resolve/main/sample.webp')
input_ = preprocessor(image).unsqueeze(0)
# input_, shape: torch.Size([1, 3, 384, 384]), dtype: torch.float32
with torch.no_grad():
    output = model(input_)
    prediction = torch.sigmoid(output)[0]
# output, shape: torch.Size([1, 12476]), dtype: torch.float32
# prediction, shape: torch.Size([12476]), dtype: torch.float32

df_tags = pd.read_csv(
    hf_hub_download(repo_id=repo_id, repo_type='model', filename='selected_tags.csv'),
    keep_default_na=False
)
tags = df_tags['name']
mask = prediction.numpy() >= df_tags['best_threshold']
print(dict(zip(tags[mask].tolist(), prediction[mask].tolist())))
# {'sensitive': 0.6114680171012878,
#  '1girl': 0.9992470741271973,
#  'solo': 0.9791421890258789,
#  'looking_at_viewer': 0.735735297203064,
#  'blush': 0.7675875425338745,
#  'smile': 0.9113360643386841,
#  'short_hair': 0.7131544947624207,
#  'long_sleeves': 0.605222225189209,
#  'brown_hair': 0.5074329376220703,
#  'holding': 0.5099453926086426,
#  'dress': 0.7616127729415894,
#  'sitting': 0.5869372487068176,
#  'purple_eyes': 0.6435719728469849,
#  'flower': 0.8259618282318115,
#  'braid': 0.8305136561393738,
#  'sidelocks': 0.25697049498558044,
#  'red_hair': 0.5593942403793335,
#  'tears': 0.7834861874580383,
#  'crying': 0.32964760065078735,
#  'plant': 0.5743373036384583,
#  'blue_flower': 0.414720743894577,
#  'crown_braid': 0.5683920979499817,
#  'potted_plant': 0.525945246219635,
#  'yellow_dress': 0.3494560718536377,
#  'flower_pot': 0.32117223739624023,
#  'happy_tears': 0.1877446323633194,
#  'wiping_tears': 0.8536925911903381}
```
### Use ONNX Model For Inference

Install [dghs-imgutils](https://github.com/deepghs/imgutils) with the following command

```shell
pip install 'dghs-imgutils>=0.17.0'
```

Use `multilabel_timm_predict` function with the following code

```python
from imgutils.generic import multilabel_timm_predict

general, character, rating = multilabel_timm_predict(
    'https://huggingface.co/animetimm/caformer_m36.dbv4-full/resolve/main/sample.webp',
    repo_id='animetimm/caformer_m36.dbv4-full',
    fmt=('general', 'character', 'rating'),
)

print(general)
# {'1girl': 0.9992470145225525,
#  'solo': 0.9791421890258789,
#  'smile': 0.9113359451293945,
#  'wiping_tears': 0.8536921739578247,
#  'braid': 0.8305132985115051,
#  'flower': 0.8259615302085876,
#  'tears': 0.7834857702255249,
#  'blush': 0.7675874829292297,
#  'dress': 0.7616124153137207,
#  'looking_at_viewer': 0.7357356548309326,
#  'short_hair': 0.713154673576355,
#  'purple_eyes': 0.6435709595680237,
#  'long_sleeves': 0.6052224040031433,
#  'sitting': 0.5869368314743042,
#  'plant': 0.5743359923362732,
#  'crown_braid': 0.568390965461731,
#  'red_hair': 0.5593934655189514,
#  'potted_plant': 0.5259431600570679,
#  'holding': 0.5099461078643799,
#  'brown_hair': 0.5074328780174255,
#  'blue_flower': 0.4147205948829651,
#  'yellow_dress': 0.3494541049003601,
#  'crying': 0.32964715361595154,
#  'flower_pot': 0.32117021083831787,
#  'sidelocks': 0.2569706439971924,
#  'happy_tears': 0.1877431571483612}
print(character)
# {}
print(rating)
# {'sensitive': 0.6114680767059326}
```

For further information, see [documentation of function multilabel_timm_predict](https://dghs-imgutils.deepghs.org/main/api_doc/generic/multilabel_timm.html#multilabel-timm-predict).