yolo_finetuned_fruits

mahernto/yolo_finetuned_fruits

yolo_finetuned_fruits is a object detection model from mahernto. 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

12% of all-time downloads

All-time downloads

129

Public

Parameters

6.5M

1.6 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors25.9 MB · 100%

At a glance

Task: Object Detection
Library: transformers
License: apache-2.0
Model type: yolos
Access: Public
Created: Apr 23, 2025
Updated: Apr 26, 2025
SHA: 6a3426c5

Base models

hustvl/yolos-tiny

Model card

From the Hugging Face model README

yolo_finetuned_fruits

This model is a fine-tuned version of hustvl/yolos-tiny on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.8209
Map: 0.5813
Map 50: 0.8161
Map 75: 0.6682
Map Small: -1.0
Map Medium: 0.6283
Map Large: 0.5888
Mar 1: 0.4242
Mar 10: 0.7055
Mar 100: 0.7704
Mar Small: -1.0
Mar Medium: 0.6886
Mar Large: 0.7816
Map Banana: 0.4339
Mar 100 Banana: 0.7225
Map Orange: 0.6177
Mar 100 Orange: 0.7857
Map Apple: 0.6923
Mar 100 Apple: 0.8029

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: 5e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 30

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 Banana	Mar 100 Banana	Map Orange	Mar 100 Orange	Map Apple	Mar 100 Apple
No log	1.0	60	2.1499	0.0136	0.0448	0.0056	-1.0	0.0109	0.0158	0.075	0.1852	0.3357	-1.0	0.1843	0.3553	0.013	0.37	0.0078	0.3143	0.0201	0.3229
No log	2.0	120	1.7782	0.0292	0.0773	0.0143	-1.0	0.0276	0.0386	0.1073	0.2172	0.3738	-1.0	0.1543	0.3976	0.0311	0.5425	0.0182	0.1476	0.0383	0.4314
No log	3.0	180	1.5906	0.0594	0.1414	0.0417	-1.0	0.1115	0.0605	0.152	0.3742	0.5341	-1.0	0.4	0.5537	0.0778	0.56	0.0529	0.5167	0.0476	0.5257
No log	4.0	240	1.5383	0.0861	0.202	0.0501	-1.0	0.2612	0.0865	0.151	0.3671	0.5304	-1.0	0.45	0.5377	0.1303	0.6025	0.0745	0.5	0.0535	0.4886
No log	5.0	300	1.1837	0.1558	0.2537	0.1816	-1.0	0.2695	0.1583	0.2698	0.4915	0.6304	-1.0	0.6171	0.6306	0.1721	0.665	0.1067	0.4976	0.1887	0.7286
No log	6.0	360	1.0734	0.157	0.2964	0.1582	-1.0	0.3468	0.187	0.2915	0.5425	0.6648	-1.0	0.6343	0.6689	0.2002	0.655	0.1633	0.6881	0.1074	0.6514
No log	7.0	420	1.0573	0.2775	0.4635	0.3247	-1.0	0.4621	0.2992	0.3344	0.5898	0.6521	-1.0	0.6143	0.6591	0.2421	0.6525	0.3061	0.581	0.2844	0.7229
No log	8.0	480	1.0384	0.2976	0.4884	0.3472	-1.0	0.3785	0.3332	0.349	0.5867	0.6615	-1.0	0.5629	0.6758	0.2774	0.655	0.2988	0.6095	0.3166	0.72
1.3795	9.0	540	1.0118	0.3836	0.6136	0.4243	-1.0	0.5103	0.4155	0.3625	0.6428	0.7234	-1.0	0.6757	0.7321	0.3059	0.7025	0.418	0.7048	0.4267	0.7629
1.3795	10.0	600	0.9245	0.435	0.6491	0.5092	-1.0	0.5728	0.4373	0.3755	0.6479	0.7627	-1.0	0.67	0.7771	0.3134	0.7225	0.4386	0.7571	0.5529	0.8086
1.3795	11.0	660	0.9402	0.4402	0.6789	0.4961	-1.0	0.5685	0.4575	0.3954	0.6632	0.7531	-1.0	0.6486	0.769	0.2956	0.7225	0.4795	0.7452	0.5453	0.7914
1.3795	12.0	720	0.9860	0.4799	0.732	0.5485	-1.0	0.5748	0.4896	0.3923	0.6661	0.7248	-1.0	0.64	0.7374	0.3637	0.6825	0.4651	0.7119	0.611	0.78
1.3795	13.0	780	0.9429	0.5169	0.7922	0.5961	-1.0	0.5773	0.5318	0.3917	0.6751	0.7439	-1.0	0.6871	0.7558	0.3606	0.6675	0.5592	0.7643	0.631	0.8
1.3795	14.0	840	0.8865	0.5173	0.758	0.5911	-1.0	0.6596	0.5182	0.4012	0.678	0.7499	-1.0	0.6986	0.7576	0.3531	0.705	0.5424	0.7619	0.6563	0.7829
1.3795	15.0	900	0.8419	0.5406	0.7763	0.6074	-1.0	0.5919	0.5512	0.4255	0.6973	0.7671	-1.0	0.7114	0.7778	0.4123	0.6975	0.5349	0.7952	0.6745	0.8086
1.3795	16.0	960	0.8329	0.5395	0.7552	0.6311	-1.0	0.5883	0.5466	0.4152	0.7104	0.757	-1.0	0.7	0.7684	0.4031	0.7	0.5438	0.7738	0.6716	0.7971
0.7998	17.0	1020	0.8817	0.534	0.7852	0.6453	-1.0	0.5942	0.5434	0.3962	0.6775	0.7507	-1.0	0.71	0.7613	0.4026	0.685	0.5503	0.7643	0.6492	0.8029
0.7998	18.0	1080	0.8657	0.5663	0.8226	0.6633	-1.0	0.6353	0.5746	0.4164	0.6948	0.7529	-1.0	0.7186	0.7613	0.415	0.685	0.5936	0.7595	0.6903	0.8143
0.7998	19.0	1140	0.8733	0.5511	0.8041	0.6633	-1.0	0.5608	0.5704	0.402	0.7012	0.7453	-1.0	0.6757	0.7573	0.4056	0.7025	0.5905	0.7619	0.6572	0.7714
0.7998	20.0	1200	0.8267	0.5838	0.8199	0.6795	-1.0	0.6184	0.5922	0.4153	0.7223	0.7688	-1.0	0.7086	0.779	0.4281	0.7075	0.6191	0.7905	0.7042	0.8086
0.7998	21.0	1260	0.8072	0.5746	0.8082	0.669	-1.0	0.6242	0.5837	0.424	0.7139	0.774	-1.0	0.7086	0.7843	0.417	0.7225	0.5945	0.7881	0.7124	0.8114
0.7998	22.0	1320	0.8209	0.5833	0.8172	0.6688	-1.0	0.6298	0.5924	0.4248	0.7034	0.7666	-1.0	0.7229	0.7737	0.4388	0.7175	0.6002	0.7738	0.7108	0.8086
0.7998	23.0	1380	0.8103	0.5882	0.8115	0.6759	-1.0	0.6302	0.5949	0.4237	0.7178	0.7796	-1.0	0.7571	0.7845	0.4453	0.725	0.6136	0.7881	0.7059	0.8257
0.7998	24.0	1440	0.8106	0.5867	0.8113	0.6811	-1.0	0.6585	0.5931	0.4273	0.7175	0.7777	-1.0	0.73	0.7851	0.4353	0.7275	0.6169	0.7857	0.7077	0.82
0.6151	25.0	1500	0.8246	0.5815	0.8161	0.6787	-1.0	0.6404	0.5954	0.424	0.7167	0.7696	-1.0	0.72	0.7772	0.4355	0.7175	0.615	0.7714	0.6941	0.82
0.6151	26.0	1560	0.8168	0.5812	0.8151	0.6754	-1.0	0.6353	0.5892	0.4254	0.7088	0.7707	-1.0	0.7229	0.778	0.4366	0.725	0.6096	0.7786	0.6972	0.8086
0.6151	27.0	1620	0.8339	0.5809	0.8164	0.6778	-1.0	0.6162	0.5896	0.4188	0.7077	0.7702	-1.0	0.7057	0.7798	0.4323	0.7225	0.6103	0.7738	0.7	0.8143
0.6151	28.0	1680	0.8239	0.5779	0.8163	0.6688	-1.0	0.617	0.5864	0.4218	0.7038	0.7647	-1.0	0.6786	0.7764	0.4304	0.715	0.6121	0.7762	0.6911	0.8029
0.6151	29.0	1740	0.8207	0.5819	0.8169	0.6689	-1.0	0.6283	0.5899	0.4235	0.7046	0.767	-1.0	0.6886	0.7778	0.4342	0.72	0.6167	0.781	0.6948	0.8
0.6151	30.0	1800	0.8209	0.5813	0.8161	0.6682	-1.0	0.6283	0.5888	0.4242	0.7055	0.7704	-1.0	0.6886	0.7816	0.4339	0.7225	0.6177	0.7857	0.6923	0.8029

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

Task: Object Detection
Library: transformers
Type: yolos
License: apache-2.0
Created: Apr 23, 2025
Updated: Apr 26, 2025