mobilevit-small_rice-leaf-disease-augmented-v4_v5_fft

SodaXII/mobilevit-small_rice-leaf-disease-augmented-v4_v5_fft

mobilevit-small_rice-leaf-disease-augmented-v4_v5_fft is a image classification model from SodaXII. 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

5% of all-time downloads

All-time downloads

343

Public

Parameters

19.9 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors19.9 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: other
Model type: mobilevit
Access: Public
Created: Apr 13, 2025
Updated: Apr 15, 2025
SHA: d7d23e4a

Base models

apple/mobilevit-small

Model card

From the Hugging Face model README

mobilevit-small_rice-leaf-disease-augmented-v4_v5_fft

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

Loss: 0.3882
Accuracy: 0.9362

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: 64
eval_batch_size: 64
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_with_restarts
lr_scheduler_warmup_steps: 256
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0678	0.5	64	2.0341	0.2617
1.9896	1.0	128	1.8927	0.5067
1.768	1.5	192	1.5508	0.5336
1.3736	2.0	256	1.0992	0.6779
0.9732	2.5	320	0.7521	0.7685
0.7316	3.0	384	0.6023	0.8121
0.5769	3.5	448	0.5281	0.8121
0.5013	4.0	512	0.4605	0.8423
0.4329	4.5	576	0.4268	0.8691
0.3821	5.0	640	0.3944	0.8859
0.3602	5.5	704	0.3895	0.8859
0.3496	6.0	768	0.3827	0.8893
0.3507	6.5	832	0.3723	0.8859
0.3225	7.0	896	0.3741	0.8893
0.2924	7.5	960	0.3271	0.9027
0.2298	8.0	1024	0.3185	0.8993
0.1888	8.5	1088	0.3093	0.9094
0.1771	9.0	1152	0.2994	0.9094
0.1461	9.5	1216	0.2907	0.9128
0.1496	10.0	1280	0.3046	0.9027
0.1284	10.5	1344	0.2999	0.9027
0.1323	11.0	1408	0.2904	0.9060
0.1291	11.5	1472	0.2939	0.9128
0.1227	12.0	1536	0.2869	0.9027
0.1033	12.5	1600	0.2886	0.9128
0.0856	13.0	1664	0.3137	0.9195
0.077	13.5	1728	0.3066	0.9161
0.0672	14.0	1792	0.3010	0.9094
0.0601	14.5	1856	0.3260	0.9128
0.0469	15.0	1920	0.2773	0.9161
0.0501	15.5	1984	0.2908	0.9161
0.0518	16.0	2048	0.3022	0.9128
0.0515	16.5	2112	0.3325	0.9228
0.0537	17.0	2176	0.3087	0.9195
0.0462	17.5	2240	0.2908	0.9295
0.0406	18.0	2304	0.3139	0.9262
0.0283	18.5	2368	0.3038	0.9329
0.0196	19.0	2432	0.2968	0.9329
0.0207	19.5	2496	0.3090	0.9295
0.0248	20.0	2560	0.3097	0.9262
0.0223	20.5	2624	0.2872	0.9262
0.0205	21.0	2688	0.3517	0.9262
0.0192	21.5	2752	0.3580	0.9295
0.0238	22.0	2816	0.3922	0.9262
0.0173	22.5	2880	0.3709	0.9228
0.019	23.0	2944	0.3679	0.9295
0.0132	23.5	3008	0.3949	0.9295
0.0112	24.0	3072	0.3609	0.9329
0.0122	24.5	3136	0.3732	0.9262
0.0107	25.0	3200	0.3667	0.9295
0.0116	25.5	3264	0.3775	0.9262
0.0111	26.0	3328	0.3289	0.9262
0.0151	26.5	3392	0.3770	0.9228
0.0139	27.0	3456	0.3755	0.9228
0.0117	27.5	3520	0.4131	0.9195
0.0086	28.0	3584	0.3856	0.9262
0.0101	28.5	3648	0.3674	0.9362
0.0097	29.0	3712	0.3762	0.9396
0.0086	29.5	3776	0.4119	0.9295
0.0091	30.0	3840	0.3882	0.9362

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.1

Task: Image Classification
Library: transformers
Type: mobilevit
License: other
Created: Apr 13, 2025
Updated: Apr 15, 2025