rt_detrv2_finetuned_v1

kb0968237/rt_detrv2_finetuned_v1

rt_detrv2_finetuned_v1 is a object detection model from kb0968237. 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

9% 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 25, 2026
Updated: Aug 25, 2026
SHA: 9f377770

Base models

PekingU/rtdetr_v2_r50vd

Spaces

kb0968237/trashify_demo

Model card

From the Hugging Face model README

rt_detrv2_finetuned_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: 9.1139
Map: 0.4611
Map 50: 0.6046
Map 75: 0.5363
Map Small: 0.0028
Map Medium: 0.2985
Map Large: 0.4702
Mar 1: 0.4663
Mar 10: 0.7033
Mar 100: 0.733
Mar Small: 0.3
Mar Medium: 0.5601
Mar Large: 0.7465
Map Bin: 0.7813
Mar 100 Bin: 0.884
Map Hand: 0.5811
Mar 100 Hand: 0.7919
Map Not Bin: 0.1528
Mar 100 Not Bin: 0.6
Map Not Hand: 0.0014
Mar 100 Not Hand: 0.5667
Map Not Trash: 0.2382
Mar 100 Not Trash: 0.5865
Map Trash: 0.6675
Mar 100 Trash: 0.773
Map Trash Arm: 0.8052
Mar 100 Trash Arm: 0.9286

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: 6
eval_batch_size: 6
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
46.7874	1.0	132	11.9413	0.3148	0.452	0.346	0.0	0.1175	0.332	0.3803	0.6461	0.7152	0.0	0.3994	0.7458	0.6223	0.8321	0.471	0.7951	0.0133	0.5571	-1.0	-1.0	0.1522	0.5722	0.6222	0.7681	0.0078	0.7667
18.7225	2.0	264	10.1450	0.4333	0.5948	0.4906	0.0058	0.1839	0.4579	0.5004	0.6791	0.7335	0.15	0.5176	0.7663	0.7202	0.8679	0.5589	0.7961	0.0856	0.55	-1.0	-1.0	0.1606	0.5583	0.6116	0.7619	0.4628	0.8667
16.0945	3.0	396	9.3096	0.4614	0.6141	0.5426	0.175	0.263	0.4767	0.5309	0.6954	0.7384	0.35	0.5443	0.7633	0.7527	0.8743	0.5932	0.7941	0.0217	0.4857	-1.0	-1.0	0.1834	0.6389	0.6477	0.7708	0.5696	0.8667
14.3528	4.0	528	8.6361	0.5394	0.7209	0.6243	0.125	0.3953	0.5628	0.5713	0.7339	0.7533	0.2	0.6028	0.7795	0.7923	0.8964	0.6041	0.7971	0.1236	0.5929	-1.0	-1.0	0.2716	0.6347	0.6558	0.7655	0.7892	0.8333
13.1690	5.0	660	8.5324	0.551	0.7225	0.6418	0.1	0.3547	0.575	0.5654	0.7253	0.7414	0.2	0.5813	0.7731	0.8026	0.8914	0.6128	0.7902	0.1162	0.5857	-1.0	-1.0	0.3212	0.6056	0.6531	0.7752	0.8	0.8
12.0323	6.0	792	8.5389	0.5352	0.7186	0.6207	0.1515	0.3713	0.5566	0.5697	0.7184	0.7565	0.2	0.5506	0.7891	0.791	0.8986	0.606	0.7784	0.119	0.6	-1.0	-1.0	0.2644	0.6194	0.6647	0.7761	0.7664	0.8667
11.0336	7.0	924	8.7793	0.5286	0.7066	0.6229	0.1556	0.3725	0.5465	0.5481	0.721	0.7566	0.2	0.5591	0.7889	0.7897	0.8807	0.606	0.7892	0.05	0.6286	-1.0	-1.0	0.3023	0.6194	0.6571	0.7885	0.7664	0.8333
10.1535	8.0	1056	9.0567	0.5216	0.6953	0.5892	0.2	0.3546	0.5433	0.5492	0.7062	0.7338	0.2	0.5449	0.7652	0.7789	0.88	0.5251	0.7324	0.1079	0.5929	-1.0	-1.0	0.266	0.6083	0.6516	0.7558	0.8	0.8333
9.3969	9.0	1188	9.0235	0.5218	0.7017	0.6041	0.2	0.3736	0.5455	0.5448	0.7163	0.7442	0.2	0.5648	0.7781	0.7872	0.8857	0.5642	0.7716	0.1073	0.6071	-1.0	-1.0	0.2675	0.6056	0.6489	0.7619	0.7557	0.8333
8.8887	10.0	1320	9.0799	0.5232	0.7009	0.6069	0.1	0.3489	0.5466	0.5499	0.7119	0.7378	0.2	0.5324	0.7731	0.7828	0.8793	0.5801	0.752	0.1022	0.6	-1.0	-1.0	0.2583	0.6014	0.6491	0.7611	0.7667	0.8333

Framework versions

Transformers 5.15.0
Pytorch 2.13.0
Datasets 5.0.1
Tokenizers 0.22.2

Task: Object Detection
Library: transformers
Type: rt_detr_v2
License: apache-2.0
Created: Aug 25, 2026
Updated: Aug 25, 2026