Skip to content
ModelListedExternal
Download

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: 8.7848 Map: 0.5341 Map 50: 0.7349 Map 75: 0.6468 Map Small: 0.0002 Map...

Sourcehuggingface.co/devmab/rt_detrv2_finetuned_trashify_box_detector_v1/tree/30cd5727ff72305b292ef4170c353cebdfef8016
KindOtherBase modelPekingU/rtdetr_v2_r50vdVersionRevision 30cd572

Model source

Kind
Other
File size
161 MB
Base model
PekingU/rtdetr_v2_r50vd
Version
vRevision 30cd572
Updated
Sep 27, 2026
Downloads
9
Tasks
Object detection
Source
Hugging Face

Source description

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: 8.7848
  • Map: 0.5341
  • Map 50: 0.7349
  • Map 75: 0.6468
  • Map Small: 0.0002
  • Map Medium: 0.3539
  • Map Large: 0.5642
  • Mar 1: 0.5616
  • Mar 10: 0.6998
  • Mar 100: 0.7109
  • Mar Small: 0.1
  • Mar Medium: 0.4727
  • Mar Large: 0.7541
  • Map Bin: 0.7906
  • Mar 100 Bin: 0.8624
  • Map Hand: 0.6251
  • Mar 100 Hand: 0.7716
  • Map Not Bin: 0.1563
  • Mar 100 Not Bin: 0.5571
  • Map Not Hand: -1.0
  • Mar 100 Not Hand: -1.0
  • Map Not Trash: 0.2793
  • Mar 100 Not Trash: 0.55
  • Map Trash: 0.6638
  • Mar 100 Trash: 0.7575
  • Map Trash Arm: 0.6895
  • Mar 100 Trash Arm: 0.7667

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: 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
51.51561.09913.72050.28110.46860.30440.0750.15910.29820.36270.52460.55940.150.28860.60780.52870.79080.46590.72840.05770.4071-1.0-1.00.14470.38060.4810.61590.00860.4333
27.47462.019811.19320.36750.60130.38110.050.12260.3860.42290.61080.67670.10.39260.70230.6240.8390.50150.77160.02160.5786-1.0-1.00.18620.52780.52460.70970.34710.6333
21.32453.029710.36380.4630.65570.53480.03330.17940.48350.51180.65280.68750.10.42270.71760.70660.82980.58090.76370.04470.5143-1.0-1.00.24620.53890.58230.74510.61760.7333
17.52714.03968.99230.50530.69520.56140.00290.29140.52870.52830.69750.73170.050.4420.76850.7890.87090.63640.7980.12390.6357-1.0-1.00.2690.55280.6150.73270.59850.8
15.49065.04958.75780.52180.71010.61760.00040.32160.54690.54950.68530.71860.150.46310.75940.79150.87020.63850.78730.10720.5571-1.0-1.00.28080.57080.6380.75930.67510.7667
14.03216.05948.75540.54680.73470.64720.06670.28170.57890.56960.71790.74120.20.50230.77260.79380.87160.62070.79120.23960.6429-1.0-1.00.26680.58190.65230.75930.70750.8
12.77817.06938.65760.52270.7320.57970.03750.38510.55390.57190.7040.7290.150.550.76310.80190.87020.61830.79020.24850.6143-1.0-1.00.27350.58330.63910.74960.55520.7667
11.74208.07928.71100.5290.70110.6150.00.33640.55830.55610.69410.71590.00.4540.75780.79530.85670.61010.77350.1540.55-1.0-1.00.28720.55690.65950.75840.66760.8
10.83509.08918.77990.52470.72010.56540.00010.34690.55670.56290.69170.70660.10.46880.75080.80180.86310.61790.78040.16440.5571-1.0-1.00.28310.550.65560.75580.62550.7333
10.201010.09908.78480.53410.73490.64680.00020.35390.56420.56160.69980.71090.10.47270.75410.79060.86240.62510.77160.15630.5571-1.0-1.00.27930.550.66380.75750.68950.7667

Framework versions

  • Transformers 5.0.0
  • Pytorch 2.10.0+cu128
  • Datasets 4.8.5
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrimaryVersion 30cd5727ff72305b292ef4170c353cebdfef8016
huggingface.co/devmab/rt_detrv2_finetuned_trashify_box_detector_v1/tree/30cd5727ff72305b292ef4170c353cebdfef8016

Verified Sep 27

Model artifacts

1 artifact

model.safetensors

safetensors · 161 MB · SHA-256 501ab3395274…3ff1 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 27huggingface.co/devmab/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: 8.7848 - Map: 0.5341 - Map 50: 0.7349 - Map 75: 0.6468 - Map Small: 0.0002 - Map Medium: 0.3539 - Map Large: 0.5642 - Mar 1: 0.5616 - Mar 10: 0.6998 - Mar 100: 0.7109 - Mar Small: 0.1 - Mar Medium: 0.4727 - Mar Large: 0.7541 - Map Bin: 0.7906 - Mar 100 Bin: 0.8624 - Map Hand: 0.6251 - Mar 100 Hand: 0.7716 - Map Not Bin: 0.1563 - Mar 100 Not Bin: 0.5571 - Map Not Hand: -1.0 - Mar 100 Not Hand: -1.0 - Map Not Trash: 0.2793 - Mar 100 Not Trash: 0.55 - Map Trash: 0.6638 - Mar 100 Trash: 0.7575 - Map Trash Arm: 0.6895 - Mar 100 Trash Arm: 0.7667 ## 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: 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 | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:----...

NoteSep 27huggingface.co/devmab/rt_detrv2_finetuned_trashify_box_detector_v1

Source context: 9 downloads · 0 likes · Pipeline object-detection · Library transformers · Repo devmab/rt_detrv2_finetuned_trashify_box_detector_v1