Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import os | |
| import torch | |
| from model import create_vit | |
| from timeit import default_timer as timer | |
| from typing import Tuple, Dict | |
| # Setup class names | |
| with open("class_names.txt", "r") as f: | |
| class_names = [name.strip() for name in f.readlines()] | |
| ### Model and transforms preparation ### | |
| # Create model and transforms | |
| model, _, _, transforms = create_vit(output_shape=len(class_names), classes=class_names) | |
| # Load saved weights | |
| model.load_state_dict( | |
| torch.load(f="vit.pth", | |
| map_location=torch.device("cpu")) # load to CPU | |
| ) | |
| ### Predict function ### | |
| def predict(img) -> Tuple[Dict, float]: | |
| # Start a timer | |
| start_time = timer() | |
| # Transform the input image for use with the model | |
| img = transforms(img).unsqueeze(0) # unsqueeze = add batch dimension on 0th index | |
| # Put model into eval mode, make prediction | |
| model.eval() | |
| with torch.inference_mode(): | |
| # Pass transformed image through the model and turn the prediction logits into probaiblities | |
| pred_probs = torch.softmax(model(img).logits, dim=1) | |
| # Create a prediction label and prediction probability dictionary | |
| pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))} | |
| # Calculate pred time | |
| end_time = timer() | |
| pred_time = round(end_time - start_time, 4) | |
| # Return pred dict and pred time | |
| return pred_labels_and_probs, pred_time | |
| ### 4. Gradio app ### | |
| # Create title, description and article | |
| title = "A ViT cifar10 Classifier" | |
| description = "An [ViT feature extractor](https://huggingface.co./google/vit-base-patch16-224) computer vision model to classify images on the [10 classes of the cifar10 dataset](https://huggingface.co./datasets/cifar10). [Source Code Found Here](https://colab.research.google.com/drive/1j4NbiMpCqmXN1xw9e2_r77gMdr3WpMnO?usp=drive_link)" | |
| article = "Built with [Gradio](https://github.com/gradio-app/gradio) and [PyTorch](https://pytorch.org/). [Source Code Found Here](https://colab.research.google.com/drive/1j4NbiMpCqmXN1xw9e2_r77gMdr3WpMnO?usp=drive_link)" | |
| # Create example list | |
| example_list = [["examples/" + example] for example in os.listdir("examples")] | |
| # Create the Gradio demo | |
| demo = gr.Interface(fn=predict, # maps inputs to outputs | |
| inputs=gr.Image(type="pil"), | |
| outputs=[gr.Label(num_top_classes=5, label="Predictions"), | |
| gr.Number(label="Prediction time (s)")], | |
| examples=example_list, | |
| title=title, | |
| description=description, | |
| article=article) | |
| # Launch the demo | |
| demo.launch() | |