V3_Image_classification__points_durs__google_vit-base-patch16-224-in21k

Optikan/V3_Image_classification__points_durs__google_vit-base-patch16-224-in21k

V3_Image_classification__points_durs__google_vit-base-patch16-224-in21k is a image classification model from Optikan. 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

2% of all-time downloads

All-time downloads

444

Public

Repo size

2.7 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Dec 28, 2023
Updated: Dec 29, 2023
SHA: 5dd8ff3d

Model card

From the Hugging Face model README

V3_Image_classification__points_durs__google_vit-base-patch16-224-in21k

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0411
Accuracy: 0.9927

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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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
0.6667	1.0	15	0.5893	0.9121
0.4394	2.0	30	0.3294	0.9487
0.2685	3.0	45	0.1365	0.9707
0.0936	4.0	60	0.0752	0.9853
0.0517	5.0	75	0.0553	0.9890
0.0436	6.0	90	0.0556	0.9890
0.018	7.0	105	0.0557	0.9890
0.0189	8.0	120	0.0457	0.9890
0.013	9.0	135	0.0343	0.9927
0.0115	10.0	150	0.0270	0.9963
0.0101	11.0	165	0.0355	0.9927
0.0085	12.0	180	0.0356	0.9927
0.0079	13.0	195	0.0259	0.9963
0.0069	14.0	210	0.0345	0.9927
0.0066	15.0	225	0.0360	0.9927
0.0061	16.0	240	0.0359	0.9927
0.0059	17.0	255	0.0360	0.9927
0.0055	18.0	270	0.0368	0.9927
0.0054	19.0	285	0.0375	0.9927
0.0051	20.0	300	0.0375	0.9927
0.0049	21.0	315	0.0380	0.9927
0.0047	22.0	330	0.0380	0.9927
0.0046	23.0	345	0.0383	0.9927
0.0044	24.0	360	0.0386	0.9927
0.0043	25.0	375	0.0388	0.9927
0.0041	26.0	390	0.0388	0.9927
0.0041	27.0	405	0.0391	0.9927
0.0039	28.0	420	0.0392	0.9927
0.0038	29.0	435	0.0396	0.9927
0.0037	30.0	450	0.0397	0.9927
0.0037	31.0	465	0.0397	0.9927
0.0036	32.0	480	0.0399	0.9927
0.0035	33.0	495	0.0401	0.9927
0.0034	34.0	510	0.0402	0.9927
0.0034	35.0	525	0.0403	0.9927
0.0033	36.0	540	0.0403	0.9927
0.0033	37.0	555	0.0405	0.9927
0.0032	38.0	570	0.0406	0.9927
0.0032	39.0	585	0.0406	0.9927
0.0031	40.0	600	0.0407	0.9927
0.0031	41.0	615	0.0408	0.9927
0.0031	42.0	630	0.0408	0.9927
0.003	43.0	645	0.0409	0.9927
0.003	44.0	660	0.0410	0.9927
0.003	45.0	675	0.0410	0.9927
0.003	46.0	690	0.0410	0.9927
0.003	47.0	705	0.0410	0.9927
0.0029	48.0	720	0.0411	0.9927
0.0029	49.0	735	0.0411	0.9927
0.0029	50.0	750	0.0411	0.9927

Framework versions

Transformers 4.30.0
Pytorch 2.1.1
Datasets 2.15.0
Tokenizers 0.13.3

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Dec 28, 2023
Updated: Dec 29, 2023