Skip to content
ModelListedExternal
Download

Rt Dterv2 Finetuned Trashify Box Detector v2

This model is a fine-tuned version of PekingU/rtdetrv2r50vd on an unknown dataset. It achieves the following results on the evaluation set: Loss: 9.1936 Map: 0.4075 Map 50: 0.5406 Map 75: 0.4698 Map Small: 0.0 Map...

Sourcehuggingface.co/ironspiritjeff/rt_dterv2_finetuned_trashify_box_detector_v2/tree/82a2b2bb3db78165f0f448d5b93514cdb67a334b
KindOtherBase modelPekingU/rtdetr_v2_r50vdVersionRevision 82a2b2b

Model source

Kind
Other
File size
164 MB
Base model
PekingU/rtdetr_v2_r50vd
Version
vRevision 82a2b2b
Updated
Sep 27, 2026
Downloads
5
Tasks
Object detection
Source
Hugging Face

Source description

rt_dterv2_finetuned_trashify_box_detector_v2

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: 9.1936
  • Map: 0.4075
  • Map 50: 0.5406
  • Map 75: 0.4698
  • Map Small: 0.0
  • Map Medium: 0.2646
  • Map Large: 0.4168
  • Mar 1: 0.4747
  • Mar 10: 0.655
  • Mar 100: 0.727
  • Mar Small: 0.0
  • Mar Medium: 0.5371
  • Mar Large: 0.7467
  • Map Bin: 0.7465
  • Mar Bin: 0.8931
  • Map Hand: 0.6137
  • Mar Hand: 0.85
  • Map Not Bin: 0.0631
  • Mar Not Bin: 0.5909
  • Map Not Hand: 0.0173
  • Mar Not Hand: 0.5833
  • Map Not Trash: 0.1557
  • Mar Not Trash: 0.5992
  • Map Trash: 0.6574
  • Mar Trash: 0.8157
  • Map Trash Arm: 0.5989
  • Mar Trash Arm: 0.7571

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: 10
  • eval_batch_size: 10
  • 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 BinMap HandMar HandMap Not BinMar Not BinMap Not HandMar Not HandMap Not TrashMar Not TrashMap TrashMar TrashMap Trash ArmMar Trash Arm
70.33661.07915.77990.19620.31460.21590.00.0330.20410.21910.37690.4750.00.11190.52080.43190.75920.41050.75920.00460.3857-1.0-1.00.00820.32470.3220.62120.00.0
29.06532.015811.06260.31320.46460.35270.07770.29190.32930.32640.49970.61570.150.50630.64520.65890.85770.48060.83980.02180.55-1.0-1.00.1730.51230.54480.73450.00010.2
21.88033.023710.22860.37820.51170.41840.00.17640.40250.42360.66290.70820.00.4750.74570.70080.8690.61140.82720.10190.4571-1.0-1.00.22530.58080.61340.78140.01660.7333
18.59554.03169.34500.43780.61430.46890.12620.24910.45670.50440.69760.74250.1250.5290.78190.75910.88870.62020.83790.07120.5643-1.0-1.00.22490.54250.63710.78850.31420.8333
16.36475.03958.91720.44210.60050.48830.15240.30450.46210.57250.70840.74960.250.52390.78650.76520.88870.61080.83010.07460.5357-1.0-1.00.25320.60960.65920.80.28950.8333
14.61266.04748.90960.4690.64210.53780.18560.24120.48870.54180.71140.75390.250.57270.78890.77340.89790.60920.8320.09580.5857-1.0-1.00.2080.60140.66180.80620.46610.8
13.31447.05538.92210.47590.66070.50540.15190.30680.49240.54580.68880.7290.250.5170.75790.78740.89720.57770.82520.06030.5429-1.0-1.00.25160.58630.67030.78940.50790.7333
12.21788.06329.07370.44920.60990.51890.16130.30540.46140.55460.70350.74480.2750.51990.78150.77310.89580.53470.79220.03140.5929-1.0-1.00.12860.56160.67560.79290.55180.8333
11.34139.07119.12220.48680.66660.57020.12640.33530.50950.55590.71570.74920.20.54370.78310.77940.90630.57250.81460.13890.6071-1.0-1.00.23310.5740.67860.79290.51820.8
10.651910.07909.13950.48190.65160.55770.15180.31980.49960.5620.71480.74290.2250.53070.77460.77310.90350.56240.81460.09270.5643-1.0-1.00.2310.55340.67520.78850.5570.8333

Framework versions

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

Sources

1 source
Hugging FacePrimaryVersion 82a2b2bb3db78165f0f448d5b93514cdb67a334b
huggingface.co/ironspiritjeff/rt_dterv2_finetuned_trashify_box_detector_v2/tree/82a2b2bb3db78165f0f448d5b93514cdb67a334b

Verified Sep 27

Model artifacts

1 artifact

model.safetensors

safetensors · 164 MB · SHA-256 c1c111f8c929…c2da · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeSep 27huggingface.co/ironspiritjeff/rt_dterv2_finetuned_trashify_box_detector_v2

--- library_name: transformers license: apache-2.0 base_model: PekingU/rtdetr_v2_r50vd tags: - generated_from_trainer model-index: - name: rt_dterv2_finetuned_trashify_box_detector_v2 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_dterv2_finetuned_trashify_box_detector_v2 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: 9.1936 - Map: 0.4075 - Map 50: 0.5406 - Map 75: 0.4698 - Map Small: 0.0 - Map Medium: 0.2646 - Map Large: 0.4168 - Mar 1: 0.4747 - Mar 10: 0.655 - Mar 100: 0.727 - Mar Small: 0.0 - Mar Medium: 0.5371 - Mar Large: 0.7467 - Map Bin: 0.7465 - Mar Bin: 0.8931 - Map Hand: 0.6137 - Mar Hand: 0.85 - Map Not Bin: 0.0631 - Mar Not Bin: 0.5909 - Map Not Hand: 0.0173 - Mar Not Hand: 0.5833 - Map Not Trash: 0.1557 - Mar Not Trash: 0.5992 - Map Trash: 0.6574 - Mar Trash: 0.8157 - Map Trash Arm: 0.5989 - Mar Trash Arm: 0.7571 ## 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: 10 - eval_batch_size: 10 - 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 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 | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-------:|:-------:|:--------:|:--------:|:-----------:|:---...

NoteSep 27huggingface.co/ironspiritjeff/rt_dterv2_finetuned_trashify_box_detector_v2

Source context: 5 downloads · 0 likes · Pipeline object-detection · Library transformers · Repo ironspiritjeff/rt_dterv2_finetuned_trashify_box_detector_v2