prova_riconoscimento

raoulmago/prova_riconoscimento

prova_riconoscimento is a image classification model from raoulmago. Use it when you need a label for an image. It is set up for transformers.

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

Downloads · 30 days

10% of all-time downloads

All-time downloads

Public

Parameters

27.6M

16.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors110 MB · 100%

Parameter types

How the weights are stored.

F3227.5M · 100%

Model card

From the Hugging Face model README

prova_riconoscimento

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0
Accuracy: 1.0

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: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
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
No log	0.89	2	2.2590	0.0
No log	1.78	4	1.8278	0.0227
No log	2.67	6	1.2314	0.9697
No log	4.0	9	0.4039	1.0
1.5804	4.89	11	0.0799	1.0
1.5804	5.78	13	0.0060	1.0
1.5804	6.67	15	0.0004	1.0
1.5804	8.0	18	0.0000	1.0
0.0314	8.89	20	0.0000	1.0
0.0314	9.78	22	0.0000	1.0
0.0314	10.67	24	0.0000	1.0
0.0314	12.0	27	0.0000	1.0
0.0314	12.89	29	0.0000	1.0
0.0	13.78	31	0.0000	1.0
0.0	14.67	33	0.0000	1.0
0.0	16.0	36	0.0000	1.0
0.0	16.89	38	0.0000	1.0
0.0	17.78	40	0.0000	1.0
0.0	18.67	42	0.0000	1.0
0.0	20.0	45	0.0000	1.0
0.0	20.89	47	0.0000	1.0
0.0	21.78	49	0.0000	1.0
0.0	22.67	51	0.0000	1.0
0.0	24.0	54	0.0	1.0
0.0	24.89	56	0.0	1.0
0.0	25.78	58	0.0	1.0
0.0	26.67	60	0.0	1.0
0.0	28.0	63	0.0	1.0
0.0	28.89	65	0.0	1.0
0.0	29.78	67	0.0	1.0
0.0	30.67	69	0.0	1.0
0.0	32.0	72	0.0	1.0
0.0	32.89	74	0.0	1.0
0.0	33.78	76	0.0	1.0
0.0	34.67	78	0.0	1.0
0.0	36.0	81	0.0	1.0
0.0	36.89	83	0.0	1.0
0.0	37.78	85	0.0	1.0
0.0	38.67	87	0.0	1.0
0.0	40.0	90	0.0	1.0
0.0	40.89	92	0.0	1.0
0.0	41.78	94	0.0	1.0
0.0	42.67	96	0.0	1.0
0.0	44.0	99	0.0	1.0
0.0	44.44	100	0.0	1.0

Framework versions

Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Task: Image Classification
Library: transformers
Type: swin
Created: Mar 4, 2024
Updated: Mar 4, 2024