CoolFace
Modelpublic

Taki3d/CrackDetectionLowRes

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes15downloads
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. -->

CrackDetectionLowRes

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

  • —Accuracy: 0.9940
  • —Loss: 0.0183

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: 2e-05
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 1337
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 5.0

Training results

Training LossEpochStepAccuracyValidation Loss
0.01261.09920.98790.0344
0.07882.019040.99330.0220
0.13363.028560.99330.0222
0.00664.038080.99330.0190
0.05285.047600.99400.0183

Framework versions

  • —Transformers 4.31.0.dev0
  • —Pytorch 2.0.1+cpu
  • —Datasets 2.13.1
  • —Tokenizers 0.13.3