mobilenet_v2_fast_edge

Foxasdf/mobilenet_v2_fast_edge

mobilenet_v2_fast_edge is a image classification model from Foxasdf. Use it when you need a label for an image. It is set up for transformers. The card lists the license as other.

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

Downloads · 30 days

30% of all-time downloads

All-time downloads

Public

Parameters

2.3M

9.1 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors9.1 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: other
Model type: mobilenet_v2
Access: Public
Created: Feb 25, 2026
Updated: Feb 25, 2026
SHA: 0d4eba90

Base models

google/mobilenet_v2_1.0_224

Model card

From the Hugging Face model README

mobilenet_v2_fast_edge

This model is a fine-tuned version of google/mobilenet_v2_1.0_224 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7328
Accuracy: 0.9115
Precision: 0.8484
Recall: 0.9841
F1: 0.9112
Tp: 1612
Tn: 1622
Fp: 288
Fn: 26

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: 256
eval_batch_size: 256
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
lr_scheduler_warmup_steps: 220
num_epochs: 20
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Tp	Tn	Fp	Fn
No log	1.0	56	0.8057	0.8503	0.7814	0.9383	0.8527	1537	1480	430	101
No log	2.0	112	0.5217	0.9121	0.9414	0.8632	0.9006	1414	1822	88	224
No log	3.0	168	0.7782	0.7833	0.6850	0.9823	0.8071	1609	1170	740	29
No log	4.0	224	0.2459	0.9710	0.9717	0.9652	0.9685	1581	1864	46	57
No log	5.0	280	0.5047	0.9084	0.8501	0.9731	0.9075	1594	1629	281	44
No log	6.0	336	0.1835	0.9775	0.9863	0.9646	0.9753	1580	1888	22	58
No log	7.0	392	0.2031	0.9724	0.9831	0.9567	0.9697	1567	1883	27	71
No log	8.0	448	0.2055	0.9760	0.9874	0.9603	0.9737	1573	1890	20	65
0.4444	9.0	504	0.1977	0.9752	0.9772	0.9689	0.9730	1587	1873	37	51
0.4444	10.0	560	0.1726	0.9775	0.9962	0.9548	0.9751	1564	1904	6	74
0.4444	11.0	616	0.1562	0.9780	0.9974	0.9548	0.9757	1564	1906	4	74
0.4444	12.0	672	0.2181	0.9710	0.9621	0.9756	0.9688	1598	1847	63	40
0.4444	13.0	728	0.2055	0.9777	0.9756	0.9762	0.9759	1599	1870	40	39
0.4444	14.0	784	0.1394	0.9820	0.9882	0.9725	0.9803	1593	1891	19	45
0.4444	15.0	840	0.1986	0.9715	0.9729	0.9652	0.9690	1581	1866	44	57
0.4444	16.0	896	0.1493	0.9769	0.9826	0.9670	0.9748	1584	1882	28	54
0.4444	17.0	952	0.1573	0.9789	0.9851	0.9689	0.9769	1587	1886	24	51
0.2877	18.0	1008	0.1870	0.9817	0.9834	0.9768	0.9801	1600	1883	27	38
0.2877	19.0	1064	0.1390	0.9800	0.9882	0.9683	0.9781	1586	1891	19	52
0.2877	20.0	1120	0.7328	0.9115	0.8484	0.9841	0.9112	1612	1622	288	26

Framework versions

Transformers 5.2.0
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.2

Task: Image Classification
Library: transformers
Type: mobilenet_v2
License: other
Created: Feb 25, 2026
Updated: Feb 25, 2026