mobilenetv3-HandwritingStrip-3class-v2

MinhLe999/mobilenetv3-HandwritingStrip-3class-v2

mobilenetv3-HandwritingStrip-3class-v2 is a machine learning model from MinhLe999. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

12% of all-time downloads

All-time downloads

Public

Parameters

4.2M

17.1 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors17 MB · 99%

At a glance

Library: transformers
Model type: mobilenet_v3_binary
Access: Public
Created: Mar 9, 2026
Updated: Mar 9, 2026
SHA: 47cfd03e

Model card

From the Hugging Face model README

mobilenetv3-HandwritingStrip-3class-v2

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0548
Accuracy: 0.9913
Precision: 0.9899
Recall: 0.9887
F1: 0.9893
Roc Auc: 0.9986

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: 0.0003
train_batch_size: 32
eval_batch_size: 32
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: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
0.1771	0.0466	30	0.6308	0.7616	0.7977	0.7668	0.7543	0.9642
0.1758	0.0932	60	0.4830	0.8437	0.8652	0.8342	0.8363	0.9752
0.1691	0.1398	90	0.5730	0.8297	0.8744	0.7635	0.7676	0.9781
0.1806	0.1863	120	0.1443	0.9520	0.9435	0.9451	0.9440	0.9934
0.1599	0.2329	150	0.1325	0.9590	0.9629	0.9404	0.9492	0.9962
0.1087	0.2795	180	0.1342	0.9546	0.9577	0.9352	0.9436	0.9947
0.1241	0.3261	210	0.0832	0.9721	0.9679	0.9658	0.9668	0.9971
0.1201	0.3727	240	0.1240	0.9607	0.9653	0.9460	0.9534	0.9949
0.0803	0.4193	270	0.1077	0.9677	0.9673	0.9582	0.9622	0.9948
0.0970	0.4658	300	0.0660	0.9808	0.9819	0.9728	0.9769	0.9983
0.1167	0.5124	330	0.0834	0.9721	0.9687	0.9648	0.9667	0.9968
0.1077	0.5590	360	0.0884	0.9729	0.9688	0.9667	0.9677	0.9965
0.0628	0.6056	390	0.0959	0.9729	0.9693	0.9671	0.9681	0.9969
0.1763	0.6522	420	0.1187	0.9686	0.9685	0.9582	0.9629	0.9957
0.0488	0.6988	450	0.0594	0.9799	0.9753	0.9773	0.9762	0.9988
0.0817	0.7453	480	0.0624	0.9790	0.9752	0.9743	0.9747	0.9984
0.0553	0.7919	510	0.0653	0.9747	0.9744	0.9645	0.9689	0.9984
0.1238	0.8385	540	0.0684	0.9773	0.9733	0.9723	0.9728	0.9976
0.1450	0.8851	570	0.0820	0.9755	0.9746	0.9657	0.9697	0.9972
0.0451	0.9317	600	0.0665	0.9825	0.9814	0.9759	0.9785	0.9981
0.0918	0.9783	630	0.0680	0.9773	0.9730	0.9732	0.9730	0.9985
0.0784	1.0248	660	0.0576	0.9825	0.9784	0.9798	0.9791	0.9981
0.0508	1.0714	690	0.0588	0.9790	0.9789	0.9705	0.9743	0.9980
0.0694	1.1180	720	0.0837	0.9721	0.9634	0.9712	0.9667	0.9983
0.0468	1.1646	750	0.0617	0.9852	0.9845	0.9807	0.9825	0.9982
0.0261	1.2112	780	0.0675	0.9790	0.9724	0.9783	0.9751	0.9983
0.0874	1.2578	810	0.0643	0.9808	0.9761	0.9785	0.9772	0.9981
0.0458	1.3043	840	0.0620	0.9843	0.9820	0.9809	0.9815	0.9979
0.0992	1.3509	870	0.0637	0.9782	0.9716	0.9774	0.9742	0.9984
0.0770	1.3975	900	0.0704	0.9790	0.9760	0.9737	0.9748	0.9974
0.0797	1.4441	930	0.0579	0.9834	0.9827	0.9773	0.9798	0.9981
0.0296	1.4907	960	0.0652	0.9790	0.9733	0.9771	0.9751	0.9983
0.0863	1.5373	990	0.0547	0.9817	0.9775	0.9785	0.9780	0.9985
0.1118	1.5839	1020	0.0526	0.9808	0.9758	0.9780	0.9768	0.9981
0.1040	1.6304	1050	0.0650	0.9755	0.9683	0.9730	0.9705	0.9985
0.0525	1.6770	1080	0.0730	0.9755	0.9674	0.9744	0.9705	0.9983
0.0662	1.7236	1110	0.0552	0.9834	0.9798	0.9804	0.9801	0.9984
0.0214	1.7702	1140	0.0568	0.9878	0.9867	0.9834	0.9850	0.9976
0.0407	1.8168	1170	0.0561	0.9869	0.9854	0.9826	0.9839	0.9976
0.0427	1.8634	1200	0.0581	0.9852	0.9809	0.9831	0.9819	0.9977
0.0605	1.9099	1230	0.0708	0.9808	0.9759	0.9775	0.9766	0.9968
0.0506	1.9565	1260	0.0590	0.9852	0.9821	0.9815	0.9818	0.9974
0.0522	2.0031	1290	0.0569	0.9834	0.9786	0.9809	0.9797	0.9982
0.0356	2.0497	1320	0.0600	0.9834	0.9796	0.9799	0.9797	0.9977
0.0279	2.0963	1350	0.0521	0.9895	0.9888	0.9855	0.9871	0.9981
0.0175	2.1429	1380	0.0500	0.9886	0.9869	0.9853	0.9861	0.9984
0.0241	2.1894	1410	0.0813	0.9764	0.9684	0.9756	0.9715	0.9979
0.0317	2.2360	1440	0.0608	0.9869	0.9833	0.9847	0.9840	0.9980
0.0521	2.2826	1470	0.0608	0.9869	0.9829	0.9852	0.9840	0.9979
0.0199	2.3292	1500	0.0542	0.9878	0.9856	0.9844	0.9850	0.9984
0.0199	2.3758	1530	0.0538	0.9869	0.9848	0.9831	0.9839	0.9986
0.0120	2.4224	1560	0.0635	0.9843	0.9829	0.9786	0.9806	0.9982
0.0359	2.4689	1590	0.0660	0.9860	0.9850	0.9807	0.9828	0.9983
0.0417	2.5155	1620	0.0654	0.9869	0.9859	0.9820	0.9839	0.9980
0.0244	2.5621	1650	0.0643	0.9860	0.9840	0.9818	0.9829	0.9975
0.0547	2.6087	1680	0.0519	0.9878	0.9861	0.9846	0.9853	0.9982
0.0632	2.6553	1710	0.0474	0.9904	0.9891	0.9874	0.9882	0.9988
0.0065	2.7019	1740	0.0538	0.9886	0.9870	0.9853	0.9861	0.9986
0.0255	2.7484	1770	0.0571	0.9878	0.9863	0.9839	0.9851	0.9985
0.0080	2.7950	1800	0.0606	0.9878	0.9851	0.9850	0.9850	0.9985
0.0172	2.8416	1830	0.0580	0.9869	0.9848	0.9831	0.9839	0.9988
0.0250	2.8882	1860	0.0627	0.9878	0.9861	0.9840	0.9850	0.9986
0.0603	2.9348	1890	0.0624	0.9904	0.9891	0.9874	0.9882	0.9982
0.0229	2.9814	1920	0.0510	0.9904	0.9886	0.9879	0.9882	0.9987
0.0142	3.0280	1950	0.0515	0.9895	0.9883	0.9861	0.9871	0.9984
0.0070	3.0745	1980	0.0548	0.9895	0.9883	0.9861	0.9871	0.9983
0.0132	3.1211	2010	0.0536	0.9895	0.9872	0.9871	0.9872	0.9987
0.0075	3.1677	2040	0.0553	0.9878	0.9858	0.9844	0.9851	0.9984
0.0215	3.2143	2070	0.0575	0.9878	0.9858	0.9844	0.9851	0.9984
0.0020	3.2609	2100	0.0536	0.9878	0.9858	0.9844	0.9851	0.9986
0.0342	3.3075	2130	0.0532	0.9878	0.9863	0.9839	0.9851	0.9986
0.0170	3.3540	2160	0.0555	0.9878	0.9868	0.9834	0.9851	0.9985
0.0152	3.4006	2190	0.0568	0.9860	0.9826	0.9834	0.9830	0.9984
0.0011	3.4472	2220	0.0534	0.9886	0.9865	0.9858	0.9861	0.9987
0.0050	3.4938	2250	0.0567	0.9860	0.9830	0.9828	0.9829	0.9987
0.0045	3.5404	2280	0.0581	0.9878	0.9852	0.9850	0.9851	0.9986
0.0031	3.5870	2310	0.0554	0.9869	0.9845	0.9836	0.9841	0.9986
0.0075	3.6335	2340	0.0589	0.9869	0.9844	0.9836	0.9840	0.9984
0.0035	3.6801	2370	0.0596	0.9869	0.9844	0.9836	0.9840	0.9984
0.0125	3.7267	2400	0.0563	0.9895	0.9872	0.9871	0.9872	0.9986
0.0017	3.7733	2430	0.0551	0.9904	0.9892	0.9874	0.9883	0.9986
0.0074	3.8199	2460	0.0546	0.9913	0.9899	0.9887	0.9893	0.9986
0.0014	3.8665	2490	0.0547	0.9913	0.9899	0.9887	0.9893	0.9986
0.0136	3.9130	2520	0.0546	0.9913	0.9899	0.9887	0.9893	0.9986
0.0038	3.9596	2550	0.0548	0.9913	0.9899	0.9887	0.9893	0.9986

Framework versions

Transformers 5.3.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Library: transformers
Type: mobilenet_v3_binary
Created: Mar 9, 2026
Updated: Mar 9, 2026