detr_finetuned_raccoon

daniihc16/detr_finetuned_raccoon

detr_finetuned_raccoon is a object detection model from daniihc16. 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

6% of all-time downloads

All-time downloads

117

Public

Parameters

41.6M

3.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors166 MB · 100%

At a glance

Task: Object Detection
Library: transformers
License: apache-2.0
Model type: detr
Access: Public
Created: Feb 16, 2026
Updated: Feb 16, 2026
SHA: 491343c5

Base models

facebook/detr-resnet-50

Model card

From the Hugging Face model README

detr_finetuned_raccoon

This model is a fine-tuned version of facebook/detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7784
Map: 0.0755
Map 50: 0.1144
Map 75: 0.0609
Map Small: -1.0
Map Medium: 0.4602
Map Large: 0.0646
Mar 1: 0.2833
Mar 10: 0.669
Mar 100: 0.8738
Mar Small: -1.0
Mar Medium: 0.775
Mar Large: 0.8842
Map Raccoon: 0.0755
Mar 100 Raccoon: 0.8738

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: 1e-05
train_batch_size: 4
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
num_epochs: 20
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 Raccoon	Mar 100 Raccoon
No log	1.0	40	1.1544	0.0235	0.0406	0.0226	-1.0	0.1245	0.0271	0.1238	0.2619	0.85	-1.0	0.7	0.8658	0.0235	0.85
No log	2.0	80	1.1461	0.0265	0.0451	0.022	-1.0	0.1605	0.0249	0.1429	0.3548	0.8119	-1.0	0.625	0.8316	0.0265	0.8119
No log	3.0	120	0.9576	0.0295	0.0498	0.0223	-1.0	0.236	0.0253	0.0738	0.3762	0.8667	-1.0	0.725	0.8816	0.0295	0.8667
No log	4.0	160	0.9022	0.026	0.0414	0.0307	-1.0	0.1892	0.025	0.069	0.3762	0.8643	-1.0	0.725	0.8789	0.026	0.8643
No log	5.0	200	0.8727	0.032	0.0522	0.0261	-1.0	0.279	0.0272	0.1143	0.3976	0.8762	-1.0	0.725	0.8921	0.032	0.8762
No log	6.0	240	0.9133	0.025	0.0432	0.0191	-1.0	0.1766	0.0233	0.1286	0.3095	0.8548	-1.0	0.75	0.8658	0.025	0.8548
No log	7.0	280	0.7637	0.0298	0.0445	0.0349	-1.0	0.2664	0.0277	0.1619	0.4952	0.8952	-1.0	0.775	0.9079	0.0298	0.8952
No log	8.0	320	0.7977	0.031	0.0468	0.033	-1.0	0.2091	0.0277	0.1762	0.4786	0.8786	-1.0	0.75	0.8921	0.031	0.8786
No log	9.0	360	0.7815	0.0371	0.0594	0.0346	-1.0	0.3308	0.0297	0.1714	0.5048	0.8833	-1.0	0.725	0.9	0.0371	0.8833
No log	10.0	400	0.7973	0.0362	0.0545	0.0342	-1.0	0.2625	0.0355	0.2	0.519	0.8857	-1.0	0.75	0.9	0.0362	0.8857
No log	11.0	440	0.7571	0.0356	0.0527	0.0374	-1.0	0.2172	0.0368	0.1905	0.519	0.8905	-1.0	0.75	0.9053	0.0356	0.8905
No log	12.0	480	0.8602	0.0375	0.0576	0.042	-1.0	0.2926	0.0389	0.2238	0.55	0.8571	-1.0	0.75	0.8684	0.0375	0.8571
0.9417	13.0	520	0.7469	0.0682	0.1025	0.0616	-1.0	0.3313	0.0613	0.2333	0.6333	0.8881	-1.0	0.775	0.9	0.0682	0.8881
0.9417	14.0	560	0.7905	0.0589	0.0923	0.0501	-1.0	0.2517	0.0524	0.2238	0.6333	0.8667	-1.0	0.725	0.8816	0.0589	0.8667
0.9417	15.0	600	0.7784	0.0755	0.1144	0.0609	-1.0	0.4602	0.0646	0.2833	0.669	0.8738	-1.0	0.775	0.8842	0.0755	0.8738
0.9417	16.0	640	0.7640	0.0731	0.1077	0.0686	-1.0	0.4452	0.0616	0.3452	0.6429	0.8833	-1.0	0.725	0.9	0.0731	0.8833
0.9417	17.0	680	0.7819	0.0746	0.1095	0.0617	-1.0	0.4224	0.0639	0.3476	0.6762	0.8738	-1.0	0.725	0.8895	0.0746	0.8738
0.9417	18.0	720	0.7425	0.0752	0.1122	0.0604	-1.0	0.4406	0.0634	0.319	0.6571	0.8929	-1.0	0.75	0.9079	0.0752	0.8929
0.9417	19.0	760	0.7364	0.0703	0.1062	0.057	-1.0	0.4102	0.0631	0.3048	0.65	0.8833	-1.0	0.75	0.8974	0.0703	0.8833
0.9417	20.0	800	0.7439	0.0714	0.1079	0.0591	-1.0	0.4084	0.0655	0.3024	0.6595	0.8857	-1.0	0.75	0.9	0.0714	0.8857

Framework versions

Transformers 4.57.6
Pytorch 2.9.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Task: Object Detection
Library: transformers
Type: detr
License: apache-2.0
Created: Feb 16, 2026
Updated: Feb 16, 2026