|
--- |
|
tags: |
|
- autotrain |
|
- image-classification |
|
- vision |
|
datasets: |
|
- CXR-Classifier/autotrain-data |
|
license: apache-2.0 |
|
pipeline_tag: image-classification |
|
--- |
|
|
|
# CXR-Classifier(Small-size model) |
|
|
|
It is a fine tuned version of [Vision Transformer(base-sized model)](https://huggingface.co/google/vit-base-patch16-224). It was trained on a private dataset. |
|
|
|
## 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. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, also at resolution 224x224. |
|
|
|
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. |
|
|
|
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. |
|
|
|
It was introduced in the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Dosovitskiy et al. and first released in [this repository](https://github.com/google-research/vision_transformer). However, the weights were converted from the [timm repository](https://github.com/rwightman/pytorch-image-models) by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him |
|
|
|
## Validation Metrics |
|
loss: 0.1180819422006607 |
|
|
|
f1: 0.9755686604886269 |
|
|
|
precision: 0.9780405405405406 |
|
|
|
recall: 0.973109243697479 |
|
|
|
auc: 0.9916270580630442 |
|
|
|
accuracy: 0.9644607843137255 |
|
|
|
## How to use |
|
Here is how to use this model to identify a pneumonia from a chest x-ray image. |
|
|
|
```python |
|
from transformers import AutoImageProcessor, AutoModelForImageClassification |
|
from PIL import Image |
|
import requests |
|
|
|
processor = AutoImageProcessor.from_pretrained("NeuronZero/CXR-Classifier") |
|
model = AutoModelForImageClassification.from_pretrained("NeuronZero/CXR-Classifier") |
|
|
|
#dataset URL: "https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia |
|
|
|
image_url = "https://storage.googleapis.com/kagglesdsdata/datasets/17810/23812/chest_xray/test/PNEUMONIA/person100_bacteria_482.jpeg?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=databundle-worker-v2%40kaggle-161607.iam.gserviceaccount.com%2F20240406%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20240406T182943Z&X-Goog-Expires=345600&X-Goog-SignedHeaders=host&X-Goog-Signature=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" |
|
image = Image.open(requests.get(image_url, stream=True).raw) |
|
|
|
inputs = processor(images=image, return_tensors="pt") |
|
outputs = model(**inputs) |
|
logits = outputs.logits |
|
predicted_class_idx = logits.argmax(-1).item() |
|
print("Predicted class:", model.config.id2label[predicted_class_idx]) |
|
``` |
