Modelpublic

SaladSlayer00/image_classification_resnet

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes22downloads

Model Card

SaladSlayer00/imageclassificationresnet

This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:

—Train Loss: 1.2581
—Validation Loss: 1.6399
—Validation Accuracy: 0.5823
—Epoch: 11

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': 'AdamWeightDecay', 'learningrate': 5e-05, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weightdecay_rate': 0.01}
—training_precision: float32

Training results

Train Loss	Validation Loss	Validation Accuracy	Epoch
7.0750	4.8746	0.0090	0
4.6468	4.5229	0.0538	1
4.3211	4.1033	0.1209	2
3.8784	3.6736	0.1859	3
3.4274	3.2193	0.2419	4
3.0071	2.8524	0.3012	5
2.6239	2.5632	0.3651	6
2.2925	2.2959	0.4233	7
1.9792	2.1138	0.4882	8
1.7199	1.9271	0.5174	9
1.4845	1.7643	0.5666	10
1.2581	1.6399	0.5823	11

Framework versions

—Transformers 4.36.2
—TensorFlow 2.15.0
—Datasets 2.16.0
—Tokenizers 0.15.0