Aller au contenu
ModelPrésentéExterne
Télécharger

Rt Detrv2 Finetuned Trashify Box Detector v1

This model is a fine-tuned version of PekingU/rtdetrv2r50vd on an unknown dataset. It achieves the following results on the evaluation set: Loss: 9.3574 Map: 0.4888 Map 50: 0.6368 Map 75: 0.5489 Map Small: 0.2538 Map...

Sourcehuggingface.co/RahulKate-173/rt_detrv2_finetuned_trashify_box_detector_v1/tree/f6efd0040e4cce26a470f21009af48b113a90b47
TypeOtherModèle de basePekingU/rtdetr_v2_r50vdVersionRevision f6efd00

Source du modèle

Type
Other
Taille du fichier
161 MB
Modèle de base
PekingU/rtdetr_v2_r50vd
Version
vRevision f6efd00
Mis à jour
27 sept. 2026
Téléchargements
6
Tâches
Détection d'objets
Source
Hugging Face

Description de la source

rt_detrv2_finetuned_trashify_box_detector_v1

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: 9.3574
  • Map: 0.4888
  • Map 50: 0.6368
  • Map 75: 0.5489
  • Map Small: 0.2538
  • Map Medium: 0.2613
  • Map Large: 0.5114
  • Mar 1: 0.5262
  • Mar 10: 0.6702
  • Mar 100: 0.6974
  • Mar Small: 0.5
  • Mar Medium: 0.4839
  • Mar Large: 0.7304
  • Map Bin: 0.7898
  • Mar 100 Bin: 0.8621
  • Map Hand: 0.544
  • Mar 100 Hand: 0.7273
  • Map Not Bin: 0.1841
  • Mar 100 Not Bin: 0.4857
  • Map Not Hand: 0.0236
  • Mar 100 Not Hand: 0.55
  • Map Not Trash: 0.3311
  • Mar 100 Not Trash: 0.5929
  • Map Trash: 0.665
  • Mar 100 Trash: 0.7641
  • Map Trash Arm: 0.8838
  • Mar 100 Trash Arm: 0.9

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: 2
  • eval_batch_size: 2
  • 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: 0.05
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossMapMap 50Map 75Map SmallMap MediumMap LargeMar 1Mar 10Mar 100Mar SmallMar MediumMar LargeMap BinMar 100 BinMap HandMar 100 HandMap Not BinMar 100 Not BinMap Not HandMar 100 Not HandMap Not TrashMar 100 Not TrashMap TrashMar 100 TrashMap Trash ArmMar 100 Trash Arm
39.72931.045112.28250.27970.41880.29540.1010.14320.29340.32930.56610.61170.10.48220.61770.58940.79560.39250.70290.02050.38570.0340.40.15480.44390.50350.70410.26290.85
20.17422.09029.89350.43250.57190.4780.2690.20570.45110.48890.63830.71510.40.5650.73190.7510.87830.5780.79060.0230.55710.03170.50.26120.59590.60860.75860.77390.925
17.31853.013539.67500.43590.61580.44960.15230.2130.46910.45210.6680.69260.40.55920.70930.75260.86210.61260.78350.11040.50710.12720.50.22180.6010.61650.74480.61030.85
15.49084.018048.97070.44460.60850.51440.27810.29490.47890.49290.63170.70550.450.59160.70850.76320.8650.59140.78060.09870.54290.05070.60.27650.5980.64660.75240.68520.8
14.01645.022559.09200.45860.62730.5410.15840.29270.49420.51050.67940.71460.40.60.7330.7570.87340.58070.75830.09810.56430.15180.60.26550.62040.66870.78550.68870.8
12.84996.027069.17320.49220.64990.56990.40970.2760.52850.51970.69040.71320.550.58080.72990.7880.87390.5870.76760.11180.48570.15310.60.29980.6020.66980.78830.83560.875
11.79967.031579.19620.46780.61260.51930.25350.20450.48760.52030.67960.71360.450.55560.73210.77150.86010.55930.76910.16980.54290.02130.50.27390.61120.66170.78690.81730.925
10.71668.036089.03760.49490.65060.57580.21410.20320.54060.53690.67660.70330.450.50560.73520.7980.87830.5550.74820.17050.50710.10140.550.31610.58980.67860.77450.84460.875
9.79519.040599.21880.48460.63410.55830.25590.27010.5130.52040.67060.69960.50.48510.73330.78820.87140.54870.73880.16250.48570.05090.550.32470.6010.66640.77520.85080.875
9.090610.045109.35740.48880.63680.54890.25380.26130.51140.52620.67020.69740.50.48390.73040.78980.86210.5440.72730.18410.48570.02360.550.33110.59290.6650.76410.88380.9

Framework versions

  • Transformers 5.0.0
  • Pytorch 2.10.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrincipalVersion f6efd0040e4cce26a470f21009af48b113a90b47
huggingface.co/RahulKate-173/rt_detrv2_finetuned_trashify_box_detector_v1/tree/f6efd0040e4cce26a470f21009af48b113a90b47

Vérifié 27 sept.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 161 MB · SHA-256 85187871f16a…56c4 · Hugging Face

Télécharger

Extraits de sources

2 extraits
Readme27 sept.huggingface.co/RahulKate-173/rt_detrv2_finetuned_trashify_box_detector_v1

--- library_name: transformers license: apache-2.0 base_model: PekingU/rtdetr_v2_r50vd tags: - generated_from_trainer model-index: - name: rt_detrv2_finetuned_trashify_box_detector_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. --> # rt_detrv2_finetuned_trashify_box_detector_v1 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: 9.3574 - Map: 0.4888 - Map 50: 0.6368 - Map 75: 0.5489 - Map Small: 0.2538 - Map Medium: 0.2613 - Map Large: 0.5114 - Mar 1: 0.5262 - Mar 10: 0.6702 - Mar 100: 0.6974 - Mar Small: 0.5 - Mar Medium: 0.4839 - Mar Large: 0.7304 - Map Bin: 0.7898 - Mar 100 Bin: 0.8621 - Map Hand: 0.544 - Mar 100 Hand: 0.7273 - Map Not Bin: 0.1841 - Mar 100 Not Bin: 0.4857 - Map Not Hand: 0.0236 - Mar 100 Not Hand: 0.55 - Map Not Trash: 0.3311 - Mar 100 Not Trash: 0.5929 - Map Trash: 0.665 - Mar 100 Trash: 0.7641 - Map Trash Arm: 0.8838 - Mar 100 Trash Arm: 0.9 ## 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: 2 - eval_batch_size: 2 - 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: 0.05 - 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 100 Bin | Map Hand | Mar 100 Hand | Map Not Bin | Mar 100 Not Bin | Map Not Hand | Mar 100 Not Hand | Map Not Trash | Mar 100 Not Trash | Map Trash | Mar 100 Trash | Map Trash Arm | Mar 100 Trash Arm | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-----...

Note27 sept.huggingface.co/RahulKate-173/rt_detrv2_finetuned_trashify_box_detector_v1

Source context: 6 downloads · 1 likes · Pipeline object-detection · Library transformers · Repo RahulKate-173/rt_detrv2_finetuned_trashify_box_detector_v1