mobilenetv3-HandwritingStrip-v4

MinhLe999/mobilenetv3-HandwritingStrip-v4

mobilenetv3-HandwritingStrip-v4 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

4% of all-time downloads

All-time downloads

Public

Parameters

4.2M

33.9 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors16.9 MB · 100%

At a glance

Library: transformers
Model type: mobilenet_v3_binary
Access: Public
Created: Mar 4, 2026
Updated: Mar 4, 2026
SHA: 7c9447ee

Base models

MinhLe999/mobilenetv3-HandwritingStrip-RandImg

Model card

From the Hugging Face model README

mobilenetv3-blur-detection-v5

This model is a fine-tuned version of MinhLe999/mobilenetv3-HandwritingStrip-RandImg on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0821
Accuracy: 0.9762
Precision: 0.9717
Recall: 0.9717
F1: 0.9717
Roc Auc: 0.9960

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: 64
eval_batch_size: 64
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: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
0.7730	0.1351	10	1.1284	0.6480	0.9545	0.1700	0.2887	0.8624
0.1923	0.2703	20	0.3407	0.8367	0.9521	0.6437	0.7681	0.9664
0.1820	0.4054	30	0.3023	0.8844	0.9786	0.7409	0.8433	0.9791
0.1312	0.5405	40	0.3490	0.8554	0.9602	0.6842	0.7991	0.9785
0.1255	0.6757	50	0.1542	0.9541	0.9583	0.9312	0.9446	0.9894
0.1228	0.8108	60	0.1174	0.9592	0.9705	0.9312	0.9504	0.9920
0.0987	0.9459	70	0.1086	0.9626	0.9747	0.9352	0.9545	0.9937
0.0588	1.0811	80	0.0905	0.9677	0.9634	0.9595	0.9615	0.9947
0.0577	1.2162	90	0.1384	0.9507	0.9739	0.9069	0.9392	0.9910
0.0517	1.3514	100	0.0825	0.9694	0.9598	0.9676	0.9637	0.9961
0.0580	1.4865	110	0.1075	0.9626	0.9310	0.9838	0.9567	0.9963
0.0556	1.6216	120	0.1019	0.9660	0.9486	0.9717	0.96	0.9959
0.0801	1.7568	130	0.0883	0.9677	0.9597	0.9636	0.9616	0.9957
0.0404	1.8919	140	0.0907	0.9660	0.9522	0.9676	0.9598	0.9950
0.0442	2.0270	150	0.0755	0.9711	0.9637	0.9676	0.9657	0.9962
0.0213	2.1622	160	0.0734	0.9762	0.9755	0.9676	0.9715	0.9963
0.0223	2.2973	170	0.0782	0.9762	0.9755	0.9676	0.9715	0.9962
0.0220	2.4324	180	0.0838	0.9762	0.9717	0.9717	0.9717	0.9960
0.0195	2.5676	190	0.0857	0.9745	0.9677	0.9717	0.9697	0.9958
0.0134	2.7027	200	0.0822	0.9745	0.9677	0.9717	0.9697	0.9961
0.0302	2.8378	210	0.0823	0.9762	0.9717	0.9717	0.9717	0.9960
0.0215	2.9730	220	0.0821	0.9762	0.9717	0.9717	0.9717	0.9960

Framework versions

Transformers 5.2.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Library: transformers
Type: mobilenet_v3_binary
Created: Mar 4, 2026
Updated: Mar 4, 2026