Spaces:
Sleeping
Sleeping
| # # The 'app.py' file will have four major parts: | |
| # # 1. Imports and class names setup | |
| # # 2. Model and transforms preparation | |
| # # 3. Predict function ('Predict()') | |
| # # 4. Gradio app - our Gradio interface + launch command | |
| # | |
| # # # 1. Imports and class names setup | |
| import gradio as gr | |
| import os | |
| import torch | |
| from model import create_vit_model | |
| from timeit import default_timer as timer | |
| from typing import Tuple, Dict | |
| # Setup class names | |
| class_names = ["pizza", "steak", "sushi"] | |
| # # # 2. Model and transforms preparation | |
| # Create vit model | |
| vit_b_16, vit_b_16_transforms = create_vit_model( | |
| num_classes=len(class_names), | |
| ) | |
| # Load saved weights | |
| vit_b_16.load_state_dict( | |
| torch.load( | |
| f="09_pretrained_vit_b_16_feature_extractor_foodvision_mini_v2.pth", | |
| map_location=torch.device("cpu"), # load to CPU | |
| ) | |
| ) | |
| # # # 3. Predict function | |
| 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_b_16_transforms(img).unsqueeze(0) | |
| # Put model into evaluation mode and turn on inference mode | |
| vit_b_16.eval() | |
| with torch.inference_mode(): | |
| # Pass the transformed image through the model and turn the prediction logits into prediction probabilities | |
| pred_probs = torch.softmax(vit_b_16(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 | |
| # # # 4. Gradio app ### | |
| # # # Create title, description and article strings | |
| title = "FoodVision Mini V2 🍕🥩🍣" | |
| description = "An ViT Base 16 feature extractor computer vision model to classify images of food as pizza, steak or sushi." | |
| article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)." | |
| # Create examples list from "examples"/ directory | |
| example_list = [["examples/" + example] for example in os.listdir("examples")] | |
| # # # 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=3, label="Predictions"), | |
| gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs | |
| # Create the Gradio demo | |
| examples=example_list, | |
| title=title, | |
| description=description, | |
| article=article) | |
| # Launch the demo! | |
| demo.launch() |