Computer Vision
Collection
6 items • Updated • 1
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("SeyedAli/Food-Image-Classification-VIT")
model = AutoModelForImageClassification.from_pretrained("SeyedAli/Food-Image-Classification-VIT")Quick Links
Food-Image-Classification-VIT
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the food101 dataset. It achieves the following results on the evaluation set:
- eval_loss: 1.0611
- eval_accuracy: 0.7274
- eval_runtime: 411.0682
- eval_samples_per_second: 61.425
- eval_steps_per_second: 7.68
- epoch: 0.15
- step: 718
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 13
Model tree for SeyedAli/Food-Image-Classification-VIT
Base model
google/vit-base-patch16-224-in21k
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="SeyedAli/Food-Image-Classification-VIT") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")