Modelpublic

DownwardSpiral33/hands_palms_classifier_resize

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes6downloads

Model Card

DownwardSpiral33/handspalmsclassifier_resize

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: 0.0501
—Validation Loss: 1.0093
—Train Accuracy: 0.6774
—Epoch: 49

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
0.6821	0.6453	0.6452	0
0.6637	0.6372	0.6452	1
0.6512	0.6279	0.6452	2
0.6342	0.6190	0.7097	3
0.6092	0.6068	0.7097	4
0.5795	0.5944	0.7742	5
0.5557	0.5840	0.7742	6
0.5159	0.5725	0.7419	7
0.4782	0.5667	0.7419	8
0.4409	0.5991	0.6774	9
0.4026	0.6284	0.6129	10
0.3717	0.6061	0.6774	11
0.3223	0.6154	0.6452	12
0.2490	0.6326	0.7419	13
0.2393	0.6448	0.6452	14
0.1971	0.6517	0.6774	15
0.1856	0.6966	0.5806	16
0.1828	0.7499	0.6774	17
0.1416	0.6842	0.7097	18
0.1379	0.6103	0.7742	19
0.1395	0.7928	0.6774	20
0.1494	0.6574	0.7097	21
0.1075	0.6905	0.7097	22
0.0969	0.6674	0.7097	23
0.1016	0.8444	0.6452	24
0.0974	0.9260	0.6129	25
0.1400	0.8985	0.6774	26
0.0977	0.9014	0.5806	27
0.0759	0.8310	0.6452	28
0.0683	0.8327	0.6774	29
0.0670	0.8247	0.7097	30
0.0692	0.8734	0.6452	31
0.0701	0.8369	0.7097	32
0.0605	1.0525	0.6129	33
0.0847	0.9439	0.5806	34
0.0515	0.8494	0.6774	35
0.0584	0.9270	0.5806	36
0.0623	1.0442	0.5806	37
0.0532	1.0707	0.6129	38
0.0596	0.9569	0.6452	39
0.0529	0.9502	0.7097	40
0.0451	0.9873	0.6452	41
0.0465	1.0143	0.6774	42
0.0426	1.0763	0.6452	43
0.0445	1.0282	0.6452	44
0.0644	1.0912	0.6129	45
0.1811	0.9771	0.6774	46
0.1052	1.0571	0.6452	47
0.0741	1.1330	0.5484	48
0.0501	1.0093	0.6774	49

Framework versions

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