Ir para o conteúdo
ModelListadosExterno
Baixar

Manga Face Detector Dfine v1

This model is a fine-tuned version of Attach3/manga-panel-detector-dfine on the Attach3/manga109s-faces-single dataset. It achieves the following results on the evaluation set: Loss: 4.5347 Map: 0.2875 Map 50: 0.5672...

Fontehuggingface.co/Attach3/manga-face-detector-dfine-v1/tree/ac648361edb6cc0b8789525add4c32c7af51648e
TipoOtherModelo baseAttach3/manga-panel-detector-dfineVersãoRevision ac64836Bnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
39,2 MB
Modelo base
Attach3/manga-panel-detector-dfine
Versão
vRevision ac64836
Atualizado
21 de out. de 2026
Downloads
14
Fonte
Hugging Face

Descrição da fonte

manga-face-detector-dfine-v1

This model is a fine-tuned version of Attach3/manga-panel-detector-dfine on the Attach3/manga109s-faces-single dataset. It achieves the following results on the evaluation set:

  • Loss: 4.5347
  • Map: 0.2875
  • Map 50: 0.5672
  • Map 75: 0.2518
  • Map Small: 0.1438
  • Map Medium: 0.3099
  • Map Large: 0.3967
  • Mar 1: 0.0968
  • Mar 10: 0.4484
  • Mar 100: 0.5884
  • Mar Small: 0.3936
  • Mar Medium: 0.5848
  • Mar Large: 0.7378
  • Map Face: 0.2875
  • Mar 100 Face: 0.5884

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 15.0

Training results

Training LossEpochStepValidation LossMapMap 50Map 75Map SmallMap MediumMap LargeMar 1Mar 10Mar 100Mar SmallMar MediumMar LargeMap FaceMar 100 Face
15.44981.013833.77520.260.49680.24030.0990.25990.39890.0930.36320.55890.33940.57090.68450.260.5589
14.69062.027663.94150.28350.54780.25320.12210.29190.39870.09780.40860.57340.36960.57670.71060.28350.5734
14.41563.041494.08740.29640.58370.25820.1330.30830.40320.09930.430.5760.37590.57660.71790.29640.576
14.25194.055324.18490.30090.59610.26020.13860.32050.4040.09970.43890.57770.38240.57660.72080.30090.5777
14.19305.069154.24570.29810.58590.25950.14080.31180.40420.09950.4420.58110.38310.57950.72710.29810.5811
14.11946.082984.33670.29620.58650.25760.13940.31360.40290.09870.44570.58530.39320.58310.72880.29620.5853
14.04947.096814.39830.29580.58440.25980.14250.31730.40220.09790.44750.58520.39120.58220.73250.29580.5852
13.97098.0110644.44870.28550.56890.24750.14010.30440.38980.09690.44440.58660.39110.58430.73270.28550.5866
13.93789.0124474.43900.2880.5690.25360.14050.30650.39480.09770.44680.58610.38830.58370.73450.2880.5861
13.921210.0138304.46600.29110.57520.25710.14210.31130.40030.09790.44780.58650.39030.58320.73580.29110.5865
13.916911.0152134.52320.28480.56560.24580.14080.30650.38640.09620.44480.5850.38940.58060.73680.28480.585
13.888312.0165964.52030.28460.56070.25050.14030.30580.39280.09710.44630.58910.39380.5860.73730.28460.5891
13.903313.0179794.53000.29340.57640.2580.14220.31150.40470.09810.45070.58890.39510.58550.73670.29340.5889
13.887514.0193624.52890.28630.56280.25090.14240.30760.39540.09680.44560.58720.39270.58330.73670.28630.5872
13.855215.0207454.53470.28750.56720.25180.14380.30990.39670.09680.44840.58840.39360.58480.73780.28750.5884

Framework versions

  • Transformers 5.13.0
  • Pytorch 2.13.0+cu130
  • Datasets 5.0.0
  • Tokenizers 0.22.2

Fontes

1 fonte
Hugging FacePrimárioVersão ac648361edb6cc0b8789525add4c32c7af51648e
huggingface.co/Attach3/manga-face-detector-dfine-v1/tree/ac648361edb6cc0b8789525add4c32c7af51648e

Verificado 21 de out.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 39,2 MB · SHA-256 c6d5926a2a46…02c5 · Hugging Face

Baixar

Trechos de fonte

3 trechos
Readme5 de ago.huggingface.co/Attach3/manga-face-detector-dfine-v1

--- library_name: transformers license: apache-2.0 base_model: Attach3/manga-panel-detector-dfine tags: - object-detection - vision - generated_from_trainer model-index: - name: manga-face-detector-dfine-v1 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # manga-face-detector-dfine-v1 This model is a fine-tuned version of [Attach3/manga-panel-detector-dfine](https://huggingface.co/Attach3/manga-panel-detector-dfine) on the Attach3/manga109s-faces-single dataset. It achieves the following results on the evaluation set: - Loss: 4.5347 - Map: 0.2875 - Map 50: 0.5672 - Map 75: 0.2518 - Map Small: 0.1438 - Map Medium: 0.3099 - Map Large: 0.3967 - Mar 1: 0.0968 - Mar 10: 0.4484 - Mar 100: 0.5884 - Mar Small: 0.3936 - Mar Medium: 0.5848 - Mar Large: 0.7378 - Map Face: 0.2875 - Mar 100 Face: 0.5884 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 1 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 15.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Face | Mar 100 Face | |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:--------:|:------------:| | 15.4498 | 1.0 | 1383 | 3.7752 | 0.26 | 0.4968 | 0.2403 | 0.099 | 0.2599 | 0.3989 | 0.093 | 0.3632 | 0.5589 | 0.3394 | 0.5709 | 0.6845 | 0.26 | 0.5589 | | 14.6906 | 2.0 | 2766 | 3.9415 | 0.2835 | 0.5478 | 0.2532 | 0.1221 | 0.2919 | 0.3987 | 0.0978 | 0.4086 | 0.5734 | 0.3696 | 0.5767 | 0.7106 | 0.2835 | 0.5734 | | 14.4156 | 3.0 | 4149 | 4.0874 | 0.2964 | 0.5837 | 0.2582 | 0.133 | 0.3083 | 0.4032 | 0.0993 | 0.43 | 0.576 | 0.3759 | 0.5766 | 0.7179 | 0.2964 | 0....

Note21 de out.huggingface.co/Attach3/manga-face-detector-dfine-v1

Source context: 14 downloads · 0 likes · Pipeline object-detection · Library transformers · Repo Attach3/manga-face-detector-dfine-v1

Note5 de ago.huggingface.co/Attach3/manga-face-detector-dfine-v1

Source context: 188 downloads · 0 likes · Pipeline object-detection · Library transformers · Repo Attach3/manga-face-detector-dfine-v1