Spaces:
Sleeping
Sleeping
| ### 1. Imports and class names setup ### | |
| import gradio as gr | |
| import os | |
| import torch | |
| from model import createVITModel | |
| from pathlib import Path | |
| from timeit import default_timer as timer | |
| from typing import Tuple, Dict | |
| # Setup class names | |
| with open("classes.txt", "r") as f: # reading them in from class_names.txt | |
| class_names = [food_name.strip() for food_name in f.readlines()] | |
| model, vit_transform = createVITModel(out_features=len(class_names)) | |
| model.load_state_dict(torch.load('VIT_32_20_003.pth')) | |
| model = model.to('cpu') | |
| # Create a list of example inputs to our Gradio demo | |
| examples_source_dir = Path("examples") | |
| examples_source_paths = list(examples_source_dir.glob("*.jpg")) | |
| example_list = [str(filepath) for filepath in examples_source_paths] | |
| def predict(img) -> Tuple[Dict, float]: | |
| """Transforms and performs a prediction on img and returns prediction and time taken. | |
| """ | |
| # Start the timer | |
| start_time = timer() | |
| # Transform the target image and add a batch dimension | |
| img = vit_transform(img).unsqueeze(dim=0) | |
| # Put model into evaluation mode and turn on inference mode | |
| model.eval() | |
| with torch.inference_mode(): | |
| # Pass the transformed image through the model and turn the prediction logits into prediction probabilities | |
| pred_probs = torch.softmax(model(img), dim=1) | |
| # Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter) | |
| pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))} | |
| # Calculate the prediction time | |
| pred_time = round(timer() - start_time, 5) | |
| # Return the prediction dictionary and prediction time | |
| return pred_labels_and_probs, pred_time | |
| # Create title, description and article strings | |
| title = "Food Image Classifier 🍰 🎂" | |
| description = "A VIT Food Classifier." | |
| article = "" | |
| # Create the Gradio demo | |
| demo = gr.Interface(fn=predict, # mapping function from input to output | |
| inputs=gr.Image(type="pil"), # what are the inputs? | |
| outputs=[gr.Label(num_top_classes=5, label="Predictions"), # what are the outputs? | |
| gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs | |
| examples=example_list, | |
| title=title, | |
| description=description, | |
| article=article) | |
| # Launch the demo! | |
| demo.launch(debug=False) # generate a publically shareable URL? |