rt_detrv2_finetuned_trashify_box_detector_v1

arjunraim/rt_detrv2_finetuned_trashify_box_detector_v1

rt_detrv2_finetuned_trashify_box_detector_v1 is a object detection model from arjunraim. 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

28% of all-time downloads

All-time downloads

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: Aug 15, 2026
Updated: Aug 15, 2026
SHA: 57c3fd52

Base models

PekingU/rtdetr_v2_r50vd

Model card

From the Hugging Face model README

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: 9.7182
Map: 0.5436
Map 50: 0.7171
Map 75: 0.6119
Map Small: 0.0033
Map Medium: 0.2656
Map Large: 0.5772
Mar 1: 0.5789
Mar 10: 0.7361
Mar 100: 0.7501
Mar Small: 0.25
Mar Medium: 0.4568
Mar Large: 0.7846
Map Bin: 0.7728
Mar 100 Bin: 0.8709
Map Hand: 0.5724
Mar 100 Hand: 0.7833
Map Not Bin: 0.2034
Mar 100 Not Bin: 0.6
Map Not Hand: -1.0
Mar 100 Not Hand: -1.0
Map Not Trash: 0.2673
Mar 100 Not Trash: 0.5611
Map Trash: 0.6214
Mar 100 Trash: 0.785
Map Trash Arm: 0.8243
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: 16
eval_batch_size: 16
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
36.9914	1.0	50	15.1983	0.2794	0.4224	0.3057	0.0	0.0598	0.294	0.3234	0.6099	0.685	0.0	0.2392	0.74	0.6182	0.8291	0.4511	0.798	0.0303	0.5143	-1.0	-1.0	0.0868	0.4069	0.4848	0.6947	0.0051	0.8667
20.9453	2.0	100	11.0303	0.3233	0.465	0.3581	0.0375	0.1285	0.3468	0.3846	0.5876	0.7013	0.15	0.3773	0.7372	0.678	0.8397	0.4675	0.7912	0.0157	0.5643	-1.0	-1.0	0.1975	0.5403	0.5796	0.7389	0.0017	0.7333
17.2215	3.0	150	10.8097	0.3853	0.5324	0.4392	0.075	0.204	0.4142	0.4687	0.6842	0.7224	0.3	0.4091	0.7579	0.6919	0.8638	0.5571	0.8059	0.1184	0.5571	-1.0	-1.0	0.2385	0.5764	0.5479	0.7646	0.1578	0.7667
15.4263	4.0	200	9.4349	0.4839	0.6592	0.5539	0.0667	0.3427	0.5112	0.5753	0.719	0.7487	0.25	0.55	0.7877	0.7719	0.8801	0.5782	0.8176	0.085	0.6286	-1.0	-1.0	0.2351	0.5847	0.633	0.7814	0.6	0.8
13.9969	5.0	250	9.5806	0.4889	0.6798	0.5614	0.2	0.2671	0.5197	0.5459	0.7191	0.7457	0.2	0.4807	0.7794	0.766	0.8738	0.5862	0.7951	0.1639	0.6	-1.0	-1.0	0.266	0.5986	0.6114	0.7735	0.5397	0.8333
12.7851	6.0	300	9.4804	0.5345	0.723	0.5979	0.0833	0.3152	0.5702	0.5689	0.7315	0.752	0.25	0.5023	0.7894	0.7783	0.8816	0.5715	0.8088	0.2478	0.6	-1.0	-1.0	0.2463	0.6	0.6622	0.7885	0.701	0.8333
11.8681	7.0	350	9.6118	0.5263	0.7119	0.5914	0.04	0.2488	0.557	0.5853	0.7249	0.7474	0.2	0.4551	0.7846	0.7843	0.873	0.5895	0.7931	0.207	0.6071	-1.0	-1.0	0.2593	0.5847	0.6165	0.7929	0.701	0.8333
10.9883	8.0	400	9.5693	0.5397	0.7126	0.6	0.05	0.2935	0.5712	0.5951	0.7313	0.7573	0.25	0.4676	0.7961	0.7818	0.8695	0.5879	0.8059	0.2092	0.6	-1.0	-1.0	0.2601	0.5833	0.6483	0.785	0.7507	0.9
10.3375	9.0	450	9.7501	0.5115	0.6889	0.5807	0.025	0.2711	0.545	0.585	0.7331	0.756	0.25	0.4574	0.7944	0.7757	0.8688	0.5474	0.8029	0.2084	0.6429	-1.0	-1.0	0.2631	0.5708	0.6301	0.7841	0.6442	0.8667
9.8323	10.0	500	9.7182	0.5436	0.7171	0.6119	0.0033	0.2656	0.5772	0.5789	0.7361	0.7501	0.25	0.4568	0.7846	0.7728	0.8709	0.5724	0.7833	0.2034	0.6	-1.0	-1.0	0.2673	0.5611	0.6214	0.785	0.8243	0.9

Framework versions

Transformers 5.15.0
Pytorch 2.13.0+cu130
Datasets 5.0.1
Tokenizers 0.22.2

Task: Object Detection
Library: transformers
Type: rt_detr_v2
License: apache-2.0
Created: Aug 15, 2026
Updated: Aug 15, 2026