rt_detrv2_finetuned_trashify_box_detector_v1

Quantum-Monk/rt_detrv2_finetuned_trashify_box_detector_v1

rt_detrv2_finetuned_trashify_box_detector_v1 is a object detection model from Quantum-Monk. 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

5% of all-time downloads

All-time downloads

143

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 18, 2026
Updated: Jan 18, 2026
SHA: db89cb29

Base models

PekingU/rtdetr_v2_r50vd

Spaces

Quantum-Monk/trashify_demo_v4

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: 9.6423
Map: 0.5227
Map 50: 0.7138
Map 75: 0.5941
Map Small: 0.05
Map Medium: 0.2718
Map Large: 0.5486
Mar 1: 0.5579
Mar 10: 0.7102
Mar 100: 0.7442
Mar Small: 0.15
Mar Medium: 0.5659
Mar Large: 0.7689
Map Bin: 0.7657
Mar 100 Bin: 0.8816
Map Hand: 0.6027
Mar 100 Hand: 0.7951
Map Not Bin: 0.1553
Mar 100 Not Bin: 0.6286
Map Not Hand: -1.0
Mar 100 Not Hand: -1.0
Map Not Trash: 0.2737
Mar 100 Not Trash: 0.5917
Map Trash: 0.6143
Mar 100 Trash: 0.7681
Map Trash Arm: 0.7248
Mar 100 Trash Arm: 0.8

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
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 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
27.0463	1.0	50	15.4899	0.2705	0.3893	0.3055	0.025	0.069	0.2829	0.3481	0.4969	0.5391	0.05	0.2489	0.5863	0.5869	0.8454	0.4955	0.8127	0.0302	0.2571	-1.0	-1.0	0.1072	0.5222	0.4033	0.7973	0.0	0.0
17.6579	2.0	100	10.9661	0.3346	0.4669	0.3667	0.03	0.1191	0.3575	0.4088	0.6023	0.6583	0.15	0.5443	0.6936	0.6209	0.861	0.599	0.8225	0.021	0.5929	-1.0	-1.0	0.1927	0.5778	0.5731	0.7956	0.0011	0.3
16.5296	3.0	150	10.3041	0.3775	0.5146	0.4155	0.0667	0.1784	0.4033	0.4356	0.6377	0.7523	0.2	0.6085	0.7844	0.6671	0.8631	0.6256	0.8157	0.1035	0.6857	-1.0	-1.0	0.2509	0.6222	0.6036	0.7938	0.0144	0.7333
14.5736	4.0	200	9.8255	0.4818	0.657	0.549	0.0755	0.2824	0.5048	0.5649	0.7088	0.7488	0.2	0.5443	0.778	0.7252	0.883	0.6404	0.8196	0.1572	0.6	-1.0	-1.0	0.2568	0.5931	0.6036	0.7973	0.5079	0.8
20.2668	5.0	250	9.3334	0.4665	0.6285	0.5347	0.075	0.2033	0.4919	0.5653	0.7297	0.7619	0.15	0.571	0.787	0.7351	0.8844	0.6281	0.8157	0.1393	0.6429	-1.0	-1.0	0.2829	0.5944	0.6447	0.8009	0.3688	0.8333
14.1717	6.0	300	9.3199	0.503	0.6946	0.5887	0.075	0.212	0.5296	0.5867	0.7173	0.7627	0.15	0.6483	0.7833	0.7582	0.883	0.6176	0.8098	0.1768	0.7	-1.0	-1.0	0.3005	0.6139	0.6129	0.8027	0.5519	0.7667
11.9656	7.0	350	9.4737	0.5183	0.6964	0.5876	0.15	0.2405	0.5445	0.5575	0.7217	0.7499	0.15	0.5625	0.7792	0.7627	0.8801	0.5878	0.8088	0.1316	0.6071	-1.0	-1.0	0.282	0.5903	0.5958	0.7796	0.7495	0.8333
11.6564	8.0	400	9.5291	0.5383	0.7383	0.6282	0.0333	0.2741	0.565	0.5691	0.7143	0.748	0.1	0.5602	0.7749	0.7843	0.8844	0.6005	0.8	0.1929	0.6214	-1.0	-1.0	0.265	0.5944	0.626	0.7876	0.7611	0.8
11.7354	9.0	450	9.5637	0.5305	0.7275	0.6076	0.05	0.279	0.5548	0.5522	0.6963	0.7329	0.15	0.5511	0.7581	0.7739	0.8787	0.5924	0.798	0.1512	0.5357	-1.0	-1.0	0.2765	0.6	0.6277	0.785	0.7611	0.8
8.5063	10.0	500	9.6423	0.5227	0.7138	0.5941	0.05	0.2718	0.5486	0.5579	0.7102	0.7442	0.15	0.5659	0.7689	0.7657	0.8816	0.6027	0.7951	0.1553	0.6286	-1.0	-1.0	0.2737	0.5917	0.6143	0.7681	0.7248	0.8

Framework versions

Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 4.5.0
Tokenizers 0.22.2

Task: Object Detection
Library: transformers
Type: rt_detr_v2
License: apache-2.0
Created: Jan 18, 2026
Updated: Jan 18, 2026