import gradio as gr import torch from model import create_effnetb2_model from timeit import default_timer as timer # Setup class names with open("class_names.txt", "r") as f: class_names = [food_name.strip() for food_name in f.readlines()] # Create model model, transforms = create_effnetb2_model( num_classes=101, ) # Load saved weights model.load_state_dict( torch.load( f="09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth", map_location=torch.device("cpu"), # load to CPU ) ) # Create prediction code def predict(img): start_time = timer() img = transforms(img).unsqueeze(0) model.eval() with torch.inference_mode(): pred_probs = torch.softmax(model(img), dim=1) pred_labels_and_probs = { class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names)) } pred_time = round(timer() - start_time, 5) return pred_labels_and_probs, pred_time # Create Gradio app title = "FoodVision Big 🍔👁" description = "An EfficientNetB2 feature extractor computer vision model to classify images of food into 101 different classes." article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)." demo = gr.Interface( fn=predict, inputs=gr.Image(type="pil"), outputs=[ gr.Label(num_top_classes=5, label="Predictions"), gr.Number(label="Prediction time (s)"), ], examples=[["examples/04-pizza-dad.jpeg"]], interpretation="default", title=title, description=description, article=article, ) demo.launch()