hands_palms_classifier_rot02

DownwardSpiral33/hands_palms_classifier_rot02

hands_palms_classifier_rot02 is a image classification model from DownwardSpiral33. 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.

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

Downloads · 30 days

17% of all-time downloads

All-time downloads

Public

Repo size

12.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.h5343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Dec 4, 2023
Updated: Dec 4, 2023
SHA: 0192149e

Base models

google/vit-base-patch16-224-in21k

Model card

From the Hugging Face model README

DownwardSpiral33/hands_palms_classifier_rot02

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:

Train Loss: 0.2625
Validation Loss: 0.5495
Train Accuracy: 0.8387
Epoch: 48

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:

optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 17400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.6825	0.6583	0.6452	0
0.6678	0.6503	0.6452	1
0.6675	0.6464	0.6452	2
0.6613	0.6415	0.6452	3
0.6494	0.6386	0.6452	4
0.6425	0.6291	0.6452	5
0.6346	0.6174	0.6452	6
0.6238	0.6130	0.6774	7
0.6154	0.6024	0.6774	8
0.5891	0.5970	0.7419	9
0.5942	0.5873	0.7419	10
0.5802	0.5815	0.7097	11
0.5684	0.5540	0.7419	12
0.5802	0.5630	0.7097	13
0.5582	0.5820	0.6452	14
0.5363	0.5719	0.7097	15
0.5338	0.5495	0.7419	16
0.5289	0.5235	0.7742	17
0.5145	0.5370	0.7419	18
0.4930	0.5152	0.8065	19
0.4902	0.5098	0.7742	20
0.4744	0.4988	0.8387	21
0.4574	0.4835	0.8387	22
0.4609	0.5169	0.7419	23
0.4633	0.5452	0.6774	24
0.4544	0.5587	0.7097	25
0.4574	0.5251	0.7742	26
0.4523	0.4937	0.7742	27
0.4452	0.4740	0.8387	28
0.4170	0.4621	0.8065	29
0.4051	0.4820	0.8065	30
0.3928	0.4733	0.7742	31
0.3779	0.5030	0.7097	32
0.3635	0.5926	0.6452	33
0.3348	0.5447	0.7742	34
0.3406	0.5505	0.7419	35
0.3688	0.5306	0.8065	36
0.3252	0.5622	0.7097	37
0.3323	0.5813	0.7419	38
0.2871	0.6733	0.6774	39
0.2854	0.7494	0.6129	40
0.3325	0.5558	0.7742	41
0.2648	0.4954	0.8387	42
0.2584	0.5120	0.8065	43
0.2893	0.5488	0.7742	44
0.2697	0.4476	0.8387	45
0.2514	0.4976	0.8065	46
0.2198	0.4788	0.8065	47
0.2625	0.5495	0.8387	48

Framework versions

Transformers 4.35.2
TensorFlow 2.14.0
Datasets 2.15.0
Tokenizers 0.15.0

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Dec 4, 2023
Updated: Dec 4, 2023