|
--- |
|
tags: |
|
- image-classification |
|
- vision |
|
- pytorch |
|
license: apache-2.0 |
|
datasets: |
|
- cifar10 |
|
metrics: |
|
- accuracy |
|
thumbnail: https://avatars3.githubusercontent.com/u/32437151?s=460&u=4ec59abc8d21d5feea3dab323d23a5860e6996a4&v=4 |
|
--- |
|
|
|
# Vision Transformer Fine Tuned on CIFAR10 |
|
|
|
Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) and **fine-tuned on CIFAR10** at resolution 224x224. |
|
|
|
Check out the code at my [my Github repo](https://github.com/nateraw/huggingface-vit-finetune). |
|
|
|
## Usage |
|
|
|
```python |
|
from transformers import ViTFeatureExtractor, ViTForImageClassification |
|
from PIL import Image |
|
import requests |
|
|
|
url = 'https://www.cs.toronto.edu/~kriz/cifar-10-sample/dog10.png' |
|
image = Image.open(requests.get(url, stream=True).raw) |
|
feature_extractor = ViTFeatureExtractor.from_pretrained('nateraw/vit-base-patch16-224-cifar10') |
|
model = ViTForImageClassification.from_pretrained('nateraw/vit-base-patch16-224-cifar10') |
|
inputs = feature_extractor(images=image, return_tensors="pt") |
|
outputs = model(**inputs) |
|
preds = outputs.logits.argmax(dim=1) |
|
|
|
classes = [ |
|
'airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck' |
|
] |
|
classes[preds[0]] |
|
``` |
|
|
|
## Model description |
|
|
|
The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. |
|
Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder. |
|
Note that this model does not provide any fine-tuned heads, as these were zero'd by Google researchers. However, the model does include the pre-trained pooler, which can be used for downstream tasks (such as image classification). |
|
|
|
By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images for instance, you can train a standard classifier by placing a linear layer on top of the pre-trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire image. |
|
|
