Rtdetr v2 R50vd Finetuned
This model is a fine-tuned version of PekingU/rtdetrv2r50vd on an unknown dataset. It achieves the following results on the evaluation set: Loss: 10.6387 Map: 0.4061 Map 50: 0.5534 Map 75: 0.4829 Map Small: 0.0 Map...
Fonte do modelo
- Tipo
- Other
- Tamanho do arquivo
- 164 MB
- Modelo base
- PekingU/rtdetr_v2_r50vd
- Versão
- vRevision 7445fac
- Atualizado
- 21 de out. de 2026
- Downloads
- 9
- Fonte
- Hugging Face
Descrição da fonte
rtdetr_v2_r50vd_finetuned
This model is a fine-tuned version of PekingU/rtdetr_v2_r50vd on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 10.6387
- Map: 0.4061
- Map 50: 0.5534
- Map 75: 0.4829
- Map Small: 0.0
- Map Medium: 0.2252
- Map Large: 0.4158
- Mar 1: 0.4487
- Mar 10: 0.6613
- Mar 100: 0.7076
- Mar Small: 0.0
- Mar Medium: 0.5517
- Mar Large: 0.7153
- Map Bin: 0.7271
- Mar Bin: 0.8391
- Map Hand: 0.5457
- Mar Hand: 0.8222
- Map Not Bin: 0.1039
- Mar Not Bin: 0.5818
- Map Not Hand: 0.0011
- Mar Not Hand: 0.5
- Map Not Trash: 0.1534
- Mar Not Trash: 0.531
- Map Trash: 0.6285
- Mar Trash: 0.7931
- Map Trash Arm: 0.6832
- Mar Trash Arm: 0.8857
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
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 Bin | Mar Bin | Map Hand | Mar Hand | Map Not Bin | Mar Not Bin | Map Not Hand | Mar Not Hand | Map Not Trash | Mar Not Trash | Map Trash | Mar Trash | Map Trash Arm | Mar Trash Arm |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 161.0519 | 1.0 | 38 | 99.2621 | 0.0062 | 0.0143 | 0.0049 | 0.0 | 0.0003 | 0.0069 | 0.0197 | 0.0371 | 0.0409 | 0.0 | 0.0056 | 0.042 | 0.0288 | 0.1805 | 0.0058 | 0.0238 | 0.0 | 0.0 | -1.0 | -1.0 | 0.0005 | 0.0119 | 0.0021 | 0.0294 | 0.0 | 0.0 |
| 92.3532 | 2.0 | 76 | 47.3904 | 0.0516 | 0.0922 | 0.0466 | 0.0 | 0.0004 | 0.0587 | 0.1054 | 0.2537 | 0.2905 | 0.0 | 0.0167 | 0.3019 | 0.159 | 0.6391 | 0.1369 | 0.3175 | 0.0027 | 0.125 | -1.0 | -1.0 | 0.0002 | 0.0262 | 0.0088 | 0.1853 | 0.0017 | 0.45 |
| 51.7429 | 3.0 | 114 | 25.9606 | 0.1533 | 0.2403 | 0.157 | 0.0 | 0.0157 | 0.1575 | 0.2074 | 0.3622 | 0.4956 | 0.0 | 0.0917 | 0.5201 | 0.3903 | 0.8149 | 0.3225 | 0.7413 | 0.0007 | 0.225 | -1.0 | -1.0 | 0.0019 | 0.1643 | 0.204 | 0.5779 | 0.0004 | 0.45 |
| 36.4871 | 4.0 | 152 | 19.0816 | 0.2521 | 0.341 | 0.2666 | 0.0 | 0.0468 | 0.2637 | 0.2935 | 0.4408 | 0.5294 | 0.0 | 0.1222 | 0.5761 | 0.6618 | 0.9126 | 0.4209 | 0.8302 | 0.1292 | 0.3125 | -1.0 | -1.0 | 0.0153 | 0.4167 | 0.2856 | 0.7044 | 0.0 | 0.0 |
| 29.2040 | 5.0 | 190 | 15.5496 | 0.3448 | 0.4748 | 0.378 | 0.0 | 0.0877 | 0.3642 | 0.3479 | 0.562 | 0.6404 | 0.0 | 0.2583 | 0.6813 | 0.6966 | 0.8724 | 0.6193 | 0.8254 | 0.1299 | 0.5375 | -1.0 | -1.0 | 0.1299 | 0.45 | 0.4911 | 0.7574 | 0.0022 | 0.4 |
| 23.4038 | 6.0 | 228 | 12.6222 | 0.3517 | 0.4786 | 0.3773 | 0.0 | 0.1253 | 0.3774 | 0.408 | 0.583 | 0.6895 | 0.0 | 0.325 | 0.7296 | 0.6996 | 0.8483 | 0.5462 | 0.7762 | 0.1317 | 0.5875 | -1.0 | -1.0 | 0.1239 | 0.5119 | 0.5973 | 0.7632 | 0.0112 | 0.65 |
| 19.3715 | 7.0 | 266 | 11.2698 | 0.4243 | 0.5764 | 0.4679 | 0.0 | 0.1593 | 0.4462 | 0.4577 | 0.6738 | 0.742 | 0.0 | 0.4 | 0.7771 | 0.7009 | 0.8402 | 0.5957 | 0.8143 | 0.1375 | 0.6875 | -1.0 | -1.0 | 0.1096 | 0.5024 | 0.5949 | 0.7574 | 0.407 | 0.85 |
| 16.9119 | 8.0 | 304 | 10.4336 | 0.4207 | 0.5675 | 0.4626 | 0.0 | 0.1672 | 0.4496 | 0.4705 | 0.6935 | 0.7121 | 0.0 | 0.3556 | 0.7486 | 0.7338 | 0.8425 | 0.6057 | 0.7921 | 0.1816 | 0.5875 | -1.0 | -1.0 | 0.2003 | 0.5167 | 0.5747 | 0.7338 | 0.2284 | 0.8 |
| 15.4101 | 9.0 | 342 | 10.4561 | 0.4657 | 0.6568 | 0.5378 | 0.0 | 0.1921 | 0.4825 | 0.5302 | 0.6822 | 0.7427 | 0.0 | 0.4472 | 0.7692 | 0.6963 | 0.8241 | 0.5938 | 0.7873 | 0.086 | 0.6625 | -1.0 | -1.0 | 0.209 | 0.5452 | 0.5992 | 0.7368 | 0.6096 | 0.9 |
| 14.3647 | 10.0 | 380 | 10.1698 | 0.4538 | 0.6065 | 0.5107 | 0.0 | 0.1667 | 0.4779 | 0.5295 | 0.6912 | 0.7414 | 0.0 | 0.4694 | 0.7663 | 0.7725 | 0.8736 | 0.5291 | 0.7841 | 0.1604 | 0.65 | -1.0 | -1.0 | 0.2104 | 0.5833 | 0.6027 | 0.7574 | 0.448 | 0.8 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2
Fontes
1 fonte
Fontes
1 fonteVerificado 21 de out.
Artefatos de modelo
1 artefato
Artefatos de modelo
1 artefatoTrechos de fonte
3 trechos
Trechos de fonte
3 trechos--- library_name: transformers license: apache-2.0 base_model: PekingU/rtdetr_v2_r50vd tags: - generated_from_trainer model-index: - name: rtdetr_v2_r50vd_finetuned 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. --> # rtdetr_v2_r50vd_finetuned This model is a fine-tuned version of [PekingU/rtdetr_v2_r50vd](https://huggingface.co/PekingU/rtdetr_v2_r50vd) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 10.6387 - Map: 0.4061 - Map 50: 0.5534 - Map 75: 0.4829 - Map Small: 0.0 - Map Medium: 0.2252 - Map Large: 0.4158 - Mar 1: 0.4487 - Mar 10: 0.6613 - Mar 100: 0.7076 - Mar Small: 0.0 - Mar Medium: 0.5517 - Mar Large: 0.7153 - Map Bin: 0.7271 - Mar Bin: 0.8391 - Map Hand: 0.5457 - Mar Hand: 0.8222 - Map Not Bin: 0.1039 - Mar Not Bin: 0.5818 - Map Not Hand: 0.0011 - Mar Not Hand: 0.5 - Map Not Trash: 0.1534 - Mar Not Trash: 0.531 - Map Trash: 0.6285 - Mar Trash: 0.7931 - Map Trash Arm: 0.6832 - Mar Trash Arm: 0.8857 ## 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: 0.0001 - train_batch_size: 8 - eval_batch_size: 8 - 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 - lr_scheduler_warmup_steps: 500 - num_epochs: 10 - mixed_precision_training: Native AMP ### 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 Bin | Mar Bin | Map Hand | Mar Hand | Map Not Bin | Mar Not Bin | Map Not Hand | Mar Not Hand | Map Not Trash | Mar Not Trash | Map Trash | Mar Trash | Map Trash Arm | Mar Trash Arm | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-------:|:-------:|:--------:|:--------:|:-----------:|:-----------:|:------------:|:------------:|...
Source context: 9 downloads · 0 likes · Pipeline object-detection · Library transformers · Repo kweer/rtdetr_v2_r50vd_finetuned
Source context: 109 downloads · 0 likes · Pipeline object-detection · Library transformers · Repo kweer/rtdetr_v2_r50vd_finetuned
