license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
model-index:
- name: vit-base-patch16-224-franciscoflores-classification
results: []
metrics:
- accuracy
language:
- en
- es
vit-base-patch16-224-franciscoflores-classification
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the julien-c/hotdog-not-hotdog dataset. It achieves the following results on the evaluation set:
- Loss: 0.0074
- Accuracy :0.9966
Model description
Modelo de clasificacion binaria de imagenes proveniente del modelo 'google/vit-base-patch16-224-in21k', este modelo se encarga de clasificacion de imagenes de comida en donde indica cuales imagenes son comida y cuales no ///////This is a binary image classification model based on the 'google/vit-base-patch16-224-in21k' model. It is designed for classifying images of food, indicating which images depict food and which ones do not
Intended uses & limitations
More information needed
Training and evaluation data
el dataset utilizado para su entrenamiento es "sasha/dog-food" The dataset used for its training is "sasha/dog-food."
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.045 | 1.9 | 500 | 0.0828 |
| 0.0081 | 3.8 | 1000 | 0.0074 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3