ViT blur-versus-clean fine-tune
According to the model card, the model is a fine-tuned version of google/vit-base-patch16-224 on an imagefolder dataset.
Open Source Model Profile · harrytechiz
vit-base-patch16-224-blur_vs_clean
vit-base-patch16-224-blur_vs_clean is a ViT image classifier from harrytechiz for blur-versus-clean decisions. According to the model card, it is a google/vit-base-patch16-224 fine-tune reporting 97.54% evaluation accuracy.
- Publisher
- harrytechiz
- Task
- image-classification
- Model type
- vit
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
vit-base-patch16-224-blur_vs_clean is published by harrytechiz as an image-classification model. The captured configuration identifies ViTForImageClassification with model type vit. According to the model card, it is a fine-tune of google/vit-base-patch16-224 on an imagefolder dataset for blur-versus-clean classification.
Recorded capabilities
Publisher-reported 97.54% accuracy
According to the model card, the evaluation set reports loss of 0.0714 and accuracy of 0.9754.
Documented three-epoch training setup
According to the model card, training used learning rate 5e-05, batch size 32, 3 epochs, Adam with linear scheduling, and Transformers 4.31.0 with Pytorch 2.0.1.
Base-model tag reference
Hub tags record base_model:google/vit-base-patch16-224 and dataset:imagefolder, matching the card's stated base model and dataset type.
Use cases in the source record
- Binary blur-versus-clean image screening using this ViT fine-tune.
- Small-scale image-quality experiments that can reference the publisher-reported 97.54% accuracy and three-epoch training setup.
Limitations and unknowns
- No parameter count was extracted from this record.
- No independent evaluation results were extracted beyond the publisher-reported loss and accuracy.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: harrytechiz/vit-base-patch16-224-blur_vs_clean
Captured: Unknown. Processed: 2026-09-07T19:34:46.242947+00:00.
vit-base-patch16-224-blur_vs_clean 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: 0.0714 Accuracy: 0.9754 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: 5e-05 train_batch_size: 32 eval_batch_size: 32 seed: 42 gradient_accumulation_steps: 4 total_train_batch_size: 128 optimizer: Adam with betas=(0.9,0.999) and eps…
F001F002F003F004F005F006F008F009F010F011F012