Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Instructions to use vuongnhathien/vit-base-org-plot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vuongnhathien/vit-base-org-plot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="vuongnhathien/vit-base-org-plot") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("vuongnhathien/vit-base-org-plot") model = AutoModelForImageClassification.from_pretrained("vuongnhathien/vit-base-org-plot", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from vuongnhathien/vit-base-org-plot: direct link, hf CLI and curl.
- Browser
- Download file 2.3 kB
-
https://huggingface.co/vuongnhathien/vit-base-org-plot/resolve/main/README.md
- Command line
-
hf download hf://vuongnhathien/vit-base-org-plot/README.md
-
curl -L -o README.md https://huggingface.co/vuongnhathien/vit-base-org-plot/resolve/main/README.md
2.3 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-org-plot
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: vuongnhathien/30VNFoods
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.885515873015873
vit-base-org-plot
This model is a fine-tuned version of google/vit-base-patch16-224 on the vuongnhathien/30VNFoods dataset. It achieves the following results on the evaluation set:
- Loss: 0.5308
- Accuracy: 0.8855
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: 0.0003
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5888 | 1.0 | 275 | 0.6249 | 0.8179 |
| 0.2832 | 2.0 | 550 | 0.5429 | 0.8537 |
| 0.1483 | 3.0 | 825 | 0.5962 | 0.8453 |
| 0.0884 | 4.0 | 1100 | 0.5802 | 0.8573 |
| 0.034 | 5.0 | 1375 | 0.5869 | 0.8688 |
| 0.0214 | 6.0 | 1650 | 0.5424 | 0.8823 |
| 0.0088 | 7.0 | 1925 | 0.5372 | 0.8903 |
| 0.006 | 8.0 | 2200 | 0.5404 | 0.8871 |
| 0.0021 | 9.0 | 2475 | 0.5240 | 0.8915 |
| 0.0033 | 10.0 | 2750 | 0.5256 | 0.8930 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2