rt_detrv2_finetuned_trashify_box_detector_v1

Zakariya007/rt_detrv2_finetuned_trashify_box_detector_v1

rt_detrv2_finetuned_trashify_box_detector_v1 is a object detection model from Zakariya007. 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

4% of all-time downloads

All-time downloads

115

Public

Parameters

42.2M

169 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors169 MB · 100%

At a glance

Task: Object Detection
Library: transformers
License: apache-2.0
Model type: rt_detr_v2
Access: Public
Created: Feb 13, 2026
Updated: Feb 13, 2026
SHA: a99fb880

Base models

PekingU/rtdetr_v2_r50vd

Spaces

Zakariya007/trashify_demo

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: 8.8706
Map: 0.4798
Map 50: 0.6394
Map 75: 0.5681
Map Small: 0.0
Map Medium: 0.3192
Map Large: 0.5044
Mar 1: 0.5197
Mar 10: 0.7027
Mar 100: 0.7608
Mar Small: 0.0
Mar Medium: 0.5141
Mar Large: 0.7851
Map Bin: 0.7787
Mar 100 Bin: 0.8875
Map Hand: 0.6341
Mar 100 Hand: 0.8126
Map Not Bin: 0.1819
Mar 100 Not Bin: 0.6727
Map Not Hand: 0.0771
Mar 100 Not Hand: 0.7167
Map Not Trash: 0.2746
Mar 100 Not Trash: 0.6063
Map Trash: 0.6502
Mar 100 Trash: 0.7962
Map Trash Arm: 0.7623
Mar 100 Trash Arm: 0.8333

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
52.4941	1.0	99	13.4180	0.2604	0.4182	0.2913	0.0568	0.0947	0.2731	0.2788	0.4472	0.505	0.125	0.2511	0.5477	0.5146	0.788	0.4603	0.7311	0.007	0.45	-1.0	-1.0	0.1122	0.4341	0.4684	0.6267	0.0	0.0
27.0430	2.0	198	10.6845	0.3295	0.4979	0.3669	0.0793	0.141	0.3446	0.3824	0.6164	0.7114	0.1	0.4317	0.7439	0.6662	0.8187	0.537	0.7908	0.0186	0.6	-1.0	-1.0	0.1723	0.5494	0.5328	0.7344	0.0502	0.775
20.4184	3.0	297	9.6194	0.4821	0.6612	0.5651	0.1298	0.2612	0.5013	0.5274	0.6838	0.7202	0.2	0.5176	0.7498	0.7446	0.8723	0.57	0.795	0.1006	0.5929	-1.0	-1.0	0.2571	0.6059	0.636	0.755	0.5845	0.7
17.2864	4.0	396	9.0784	0.4702	0.6543	0.5386	0.1267	0.3873	0.4883	0.5334	0.6915	0.7278	0.175	0.5652	0.7558	0.7591	0.8723	0.5967	0.7924	0.1127	0.6571	-1.0	-1.0	0.2664	0.6141	0.6613	0.7557	0.4248	0.675
15.4788	5.0	495	8.6832	0.5243	0.7155	0.6272	0.0885	0.3635	0.5454	0.5353	0.6982	0.7244	0.15	0.5352	0.7582	0.7821	0.8771	0.6307	0.795	0.099	0.6071	-1.0	-1.0	0.2796	0.6071	0.6657	0.7603	0.6886	0.7
14.0935	6.0	594	8.6443	0.5403	0.7213	0.6356	0.1087	0.3988	0.5639	0.5659	0.7164	0.7517	0.15	0.5847	0.7844	0.7817	0.8807	0.6229	0.8084	0.134	0.6643	-1.0	-1.0	0.2793	0.6071	0.6796	0.7748	0.7446	0.775
12.7982	7.0	693	8.8626	0.5211	0.6944	0.6018	0.0961	0.3946	0.5445	0.5698	0.713	0.7281	0.125	0.5221	0.7663	0.7893	0.8898	0.6105	0.7924	0.126	0.5286	-1.0	-1.0	0.27	0.5859	0.6728	0.7718	0.6579	0.8
11.6979	8.0	792	9.0531	0.5146	0.6915	0.5919	0.0386	0.3927	0.537	0.5752	0.7051	0.7324	0.1	0.5613	0.7641	0.7693	0.8675	0.5779	0.7765	0.1207	0.6	-1.0	-1.0	0.2768	0.5929	0.6615	0.7573	0.6812	0.8
10.8178	9.0	891	8.9017	0.5327	0.7057	0.6097	0.0796	0.4192	0.5564	0.5932	0.7122	0.7393	0.125	0.6003	0.7686	0.7776	0.8747	0.5838	0.7807	0.134	0.5929	-1.0	-1.0	0.2907	0.5929	0.6764	0.7695	0.7337	0.825
10.0848	10.0	990	9.0344	0.5213	0.6984	0.6048	0.055	0.3787	0.5445	0.5687	0.6977	0.7293	0.1	0.5493	0.7638	0.7683	0.8614	0.5787	0.7647	0.124	0.6	-1.0	-1.0	0.2806	0.5894	0.6672	0.7603	0.7089	0.8

Framework versions

Transformers 5.0.0
Pytorch 2.9.0+cu128
Datasets 4.5.0
Tokenizers 0.22.2

Task: Object Detection
Library: transformers
Type: rt_detr_v2
License: apache-2.0
Created: Feb 13, 2026
Updated: Feb 13, 2026