Spaces:
Sleeping
Sleeping
| ### 1. Imports and class names setup ### | |
| import gradio as gr | |
| import os | |
| import torch | |
| from model import create_effnetb2_model | |
| 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 = [food.strip() for food in f.readlines()] | |
| ### 2. Model and transforms preparation ### | |
| # Create EffNetB2 model | |
| effnetb2, effnetb2_transforms = create_effnetb2_model( | |
| num_classes=101, # len(class_names) would also work | |
| ) | |
| # Load saved weights | |
| effnetb2.load_state_dict( | |
| torch.load( | |
| f="09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth", | |
| map_location=torch.device("cpu"), # load to CPU | |
| ) | |
| ) | |
| ### 3. Predict function ### | |
| # Create 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 = effnetb2_transforms(img).unsqueeze(0) | |
| # Put model into evaluation mode and turn on inference mode | |
| effnetb2.eval() | |
| with torch.inference_mode(): | |
| # Pass the transformed image through the model and turn the prediction logits into prediction probabilities | |
| pred_probs = torch.softmax(effnetb2(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 Big 🍕🥩🍣" | |
| description = "An EfficientNetB2 feature extractor computer vision model to classify 101 images of food from food101 image dataset." | |
| article = "Created as a practice" | |
| # 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(sources=["upload"], 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 | |
| # Create examples list from "examples/" directory | |
| examples=example_list, | |
| title=title, | |
| description=description, | |
| article=article) | |
| # Launch the demo! | |
| demo.launch(debug=True) | |