Modelpublic

DownwardSpiral33/hands_palms_classifier_rot01

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes5downloads

Model Card

DownwardSpiral33/handspalmsclassifier_rot01

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: 0.2863
—Validation Loss: 0.7353
—Train Accuracy: 0.6452
—Epoch: 45

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', 'weightdecay': None, 'clipnorm': None, 'globalclipnorm': None, 'clipvalue': None, 'useema': False, 'emamomentum': 0.99, 'emaoverwritefrequency': None, 'jitcompile': True, 'islegacyoptimizer': False, 'learningrate': {'module': 'keras.optimizers.schedules', 'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 1e-05, 'decaysteps': 17400, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registeredname': None}, 'beta1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
—training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.6965	0.6687	0.5806	0
0.6851	0.6601	0.6452	1
0.6753	0.6519	0.6452	2
0.6644	0.6471	0.6452	3
0.6548	0.6405	0.6129	4
0.6541	0.6340	0.6774	5
0.6436	0.6266	0.6774	6
0.6364	0.6223	0.6452	7
0.6206	0.6112	0.6774	8
0.6166	0.6024	0.6774	9
0.6150	0.5970	0.7097	10
0.6019	0.5863	0.7097	11
0.5895	0.5824	0.7097	12
0.5866	0.5862	0.7097	13
0.5813	0.5742	0.6774	14
0.5586	0.5683	0.7097	15
0.5519	0.5749	0.7419	16
0.5311	0.5906	0.6774	17
0.5440	0.5588	0.6774	18
0.5130	0.5439	0.7097	19
0.5104	0.5469	0.6452	20
0.4894	0.5574	0.6452	21
0.4903	0.5527	0.6129	22
0.4903	0.5366	0.6452	23
0.4875	0.5562	0.7097	24
0.4625	0.5090	0.7097	25
0.4532	0.5489	0.7097	26
0.4018	0.5594	0.7097	27
0.4600	0.6152	0.6774	28
0.4199	0.5669	0.6774	29
0.4406	0.6120	0.6774	30
0.3885	0.5903	0.6452	31
0.4071	0.6163	0.6452	32
0.4056	0.5257	0.7419	33
0.4037	0.5606	0.6774	34
0.3522	0.5646	0.6452	35
0.3358	0.6367	0.6774	36
0.3419	0.6752	0.6774	37
0.3567	0.5802	0.6452	38
0.3769	0.5885	0.7097	39
0.3332	0.5860	0.7097	40
0.3818	0.5612	0.7419	41
0.3463	0.5921	0.7097	42
0.3244	0.6015	0.7097	43
0.2958	0.6124	0.7097	44
0.2863	0.7353	0.6452	45

Framework versions

—Transformers 4.35.2
—TensorFlow 2.14.0
—Datasets 2.15.0
—Tokenizers 0.15.0