vit-fire-detection

Model overview

vit-fire-detection is published by EdBianchi as a ViT image-classification model. The captured configuration identifies ViTForImageClassification with model type vit, and card data records apache-2.0. According to the model card, it is a fine-tune of google/vit-base-patch16-224-in21k.

Recorded capabilities

Use cases in the source record

• Image-classification workflows for fire detection suggested by the model name and the card's reported precision and recall, with independent validation before safety use.
• Reproduction-oriented review of the card's documented hyperparameters and epoch-level training table.

Limitations and unknowns

• No parameter count was extracted from this record.
• No context-window value was extracted from this record.
• Reported loss, precision, and recall figures are publisher claims from the model card and were not independently verified.
• The training dataset is recorded as None in the captured card text, so the fine-tuning data source remains unclear.
• Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

Source: EdBianchi/vit-fire-detection

Captured: Unknown. Processed: 2026-09-07T19:34:30.609994+00:00.

vit-fire-detection This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set: Loss: 0.0126 Precision: 0.9960 Recall: 0.9960 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: 0.0002 train_batch_size: 32 eval_batch_size: 32 seed: 42 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 lr_scheduler_type: linear lr_scheduler_warmup_st…