smids_10x_deit_tiny_rms_0001_fold1

hkivancoral/smids_10x_deit_tiny_rms_0001_fold1

smids_10x_deit_tiny_rms_0001_fold1 is a image classification model from hkivancoral. Use it when you need a label for 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

38% of all-time downloads

All-time downloads

Public

Repo size

1.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin22.2 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Dec 23, 2023
Updated: Dec 23, 2023
SHA: f81478c1

Base models

facebook/deit-tiny-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

smids_10x_deit_tiny_rms_0001_fold1

This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.5641
Accuracy: 0.7746

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: 0.001
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9582	1.0	751	0.8489	0.5409
0.6559	2.0	1502	0.7002	0.6861
0.7114	3.0	2253	0.6777	0.6761
0.6817	4.0	3004	0.6465	0.6928
0.7123	5.0	3755	0.7746	0.6277
0.7345	6.0	4506	0.6493	0.7062
0.5686	7.0	5257	0.6822	0.7145
0.6113	8.0	6008	0.7258	0.6594
0.5841	9.0	6759	0.7856	0.6694
0.5988	10.0	7510	0.5594	0.7746
0.5433	11.0	8261	0.5624	0.7696
0.5465	12.0	9012	0.6273	0.7396
0.5648	13.0	9763	0.5471	0.7646
0.5274	14.0	10514	0.5762	0.7596
0.5506	15.0	11265	0.6408	0.7279
0.5782	16.0	12016	0.6203	0.7346
0.6505	17.0	12767	0.6410	0.7429
0.5965	18.0	13518	0.6045	0.7245
0.5759	19.0	14269	0.6441	0.7229
0.6397	20.0	15020	0.5941	0.7529
0.5964	21.0	15771	0.5925	0.7496
0.5874	22.0	16522	0.5857	0.7462
0.4809	23.0	17273	0.5684	0.7596
0.5688	24.0	18024	0.5817	0.7663
0.5465	25.0	18775	0.5474	0.7663
0.5665	26.0	19526	0.7830	0.6611
0.5896	27.0	20277	0.5680	0.7513
0.6236	28.0	21028	0.6568	0.6811
0.5166	29.0	21779	0.6086	0.7446
0.452	30.0	22530	0.5634	0.7579
0.4919	31.0	23281	0.5616	0.7780
0.5586	32.0	24032	0.5217	0.7679
0.4558	33.0	24783	0.5662	0.7513
0.4855	34.0	25534	0.5721	0.7613
0.4522	35.0	26285	0.5872	0.7663
0.527	36.0	27036	0.5260	0.7696
0.5143	37.0	27787	0.5855	0.7429
0.4104	38.0	28538	0.5552	0.7713
0.3918	39.0	29289	0.5587	0.7763
0.4719	40.0	30040	0.5354	0.7863
0.4591	41.0	30791	0.5453	0.7629
0.3895	42.0	31542	0.5592	0.7746
0.4622	43.0	32293	0.5533	0.7796
0.3949	44.0	33044	0.5492	0.7947
0.4199	45.0	33795	0.5523	0.7780
0.4316	46.0	34546	0.5332	0.7896
0.3892	47.0	35297	0.5380	0.7846
0.3721	48.0	36048	0.5481	0.7880
0.3964	49.0	36799	0.5559	0.7846
0.3446	50.0	37550	0.5641	0.7746

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Dec 23, 2023
Updated: Dec 23, 2023