CoolFace
Modelpublic

Woleek/camera-type

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes9downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

camera-type

This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0235
  • —Accuracy: 0.9916

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: 0.0001
  • —trainbatchsize: 10
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 5

Training results

Training LossEpochStepValidation LossAccuracy
0.00640.42000.02350.9916
0.00340.794000.03920.9941
0.00661.196000.10110.9840
0.01.588000.12270.9840
0.01.9810000.12320.9840
0.02.3712000.14330.9840
0.02.7714000.14160.9840
0.03.1616000.14080.9840
0.03.5618000.14010.9840
0.03.9520000.13940.9840
0.04.3522000.13900.9840
0.04.7424000.13890.9840

Framework versions

  • —Transformers 4.31.0
  • —Pytorch 2.0.1+cu117
  • —Datasets 2.14.4
  • —Tokenizers 0.13.3