rtdetrv2_finetuned_trashify_box_detector_v1

Kelmoir/rtdetrv2_finetuned_trashify_box_detector_v1

rtdetrv2_finetuned_trashify_box_detector_v1 is a object detection model from Kelmoir. Use it when you need objects located in an image. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

7% of all-time downloads

All-time downloads

111

Public

Parameters

42.9M

172 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors172 MB · 100%

At a glance

Task: Object Detection
Library: transformers
License: apache-2.0
Model type: rt_detr_v2
Access: Public
Created: Jan 24, 2026
Updated: Jan 24, 2026
SHA: 7a9394e8

Base models

PekingU/rtdetr_v2_r50vd

Spaces

Kelmoir/trashify_demo_v1_video

Model card

From the Hugging Face model README

rtdetrv2_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: 9.3215
Map: 0.5456
Map 50: 0.7136
Map 75: 0.6227
Map Small: 0.0
Map Medium: 0.3711
Map Large: 0.5802
Mar 1: 0.5722
Mar 10: 0.6935
Mar 100: 0.7285
Mar Small: 0.0
Mar Medium: 0.5068
Mar Large: 0.7622
Map Bin: 0.8005
Mar Bin: 0.8823
Map Hand: 0.5902
Mar Hand: 0.7539
Map Not Bin: 0.1962
Mar Not Bin: 0.6071
Map Not Hand: -1.0
Mar Not Hand: -1.0
Map Not Trash: 0.2211
Mar Not Trash: 0.4389
Map Trash: 0.6667
Mar Trash: 0.7885
Map Trash Arm: 0.7991
Mar 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: 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_ratio: 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
10.8388	1.0	99	9.1499	0.5045	0.6872	0.5749	0.075	0.3381	0.5344	0.5451	0.7097	0.7405	0.3	0.5085	0.7778	0.7808	0.8936	0.5858	0.7676	0.2115	0.6214	-1.0	-1.0	0.187	0.5736	0.6221	0.7867	0.6396	0.8
10.9884	2.0	198	9.2812	0.5164	0.6955	0.5818	0.1252	0.3818	0.5409	0.5497	0.7213	0.7607	0.45	0.5551	0.7949	0.7887	0.8879	0.5401	0.7657	0.1966	0.6929	-1.0	-1.0	0.1767	0.5653	0.6468	0.7858	0.7496	0.8667
10.4912	3.0	297	9.1873	0.5412	0.7153	0.6217	0.0026	0.3043	0.5761	0.5626	0.7161	0.7461	0.75	0.5006	0.7839	0.8086	0.8816	0.5516	0.7706	0.1984	0.6286	-1.0	-1.0	0.2276	0.5722	0.6494	0.7903	0.8112	0.8333
9.8673	4.0	396	9.3256	0.5031	0.712	0.5252	0.0625	0.3918	0.5343	0.5311	0.6931	0.7153	0.25	0.5659	0.7443	0.7747	0.861	0.5995	0.7814	0.255	0.6	-1.0	-1.0	0.1833	0.5403	0.6308	0.7761	0.5755	0.7333
9.2601	5.0	495	9.1876	0.5416	0.7069	0.6206	0.0	0.2878	0.5748	0.5615	0.6971	0.7348	0.0	0.4886	0.7725	0.7915	0.8787	0.6167	0.7775	0.1929	0.5929	-1.0	-1.0	0.2168	0.4958	0.6825	0.7973	0.7494	0.8667
8.7615	6.0	594	9.3623	0.5296	0.7233	0.5813	0.1253	0.4046	0.5575	0.5624	0.7136	0.7385	0.55	0.5335	0.7687	0.7859	0.878	0.5734	0.7588	0.2579	0.6286	-1.0	-1.0	0.2249	0.5403	0.6609	0.792	0.6744	0.8333
8.231	7.0	693	9.3799	0.5299	0.7049	0.5974	0.0025	0.3827	0.5608	0.5483	0.6916	0.7336	0.15	0.542	0.7674	0.7994	0.8816	0.567	0.7363	0.1994	0.6	-1.0	-1.0	0.2014	0.4986	0.6632	0.785	0.749	0.9
7.7591	8.0	792	9.3271	0.5383	0.7195	0.6136	0.0035	0.3713	0.5717	0.5623	0.7096	0.731	0.25	0.4949	0.7695	0.8092	0.8851	0.5745	0.7402	0.2006	0.6357	-1.0	-1.0	0.2231	0.475	0.6738	0.7832	0.7488	0.8667
7.308	9.0	891	9.2643	0.54	0.7126	0.6163	0.0	0.3795	0.5732	0.568	0.689	0.7346	0.0	0.5193	0.7689	0.7914	0.8823	0.5983	0.7627	0.1941	0.6214	-1.0	-1.0	0.2148	0.4472	0.6672	0.7938	0.7741	0.9
6.8853	10.0	990	9.3215	0.5456	0.7136	0.6227	0.0	0.3711	0.5802	0.5722	0.6935	0.7285	0.0	0.5068	0.7622	0.8005	0.8823	0.5902	0.7539	0.1962	0.6071	-1.0	-1.0	0.2211	0.4389	0.6667	0.7885	0.7991	0.9

Framework versions

Transformers 4.57.6
Pytorch 2.9.0+cu126
Datasets 4.5.0
Tokenizers 0.22.2

Task: Object Detection
Library: transformers
Type: rt_detr_v2
License: apache-2.0
Created: Jan 24, 2026
Updated: Jan 24, 2026