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 | |
| class_names = ['pizza', 'steak', 'sushi'] | |
| ### 2. Model adn transforms preparation ### | |
| effnetb2, effnetb2_transforms = create_effnetb2_model( | |
| num_classes = 3 | |
| ) | |
| # Load save weights | |
| effnetb2.load_state_dict( | |
| torch.load( | |
| f="09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth", | |
| map_location = torch.device("cpu") # load the model to the CPU | |
| ) | |
| ) | |
| ### 3. Prediction function ### | |
| def predict(img) -> Tuple[Dict, float]: | |
| #Start a timer | |
| start_time = timer() | |
| # Transform the input image for use with EffNetB2 | |
| transformed_img = effnetb2_transforms(img).unsqueeze(0) #unsqueeze = add batch dimension on 0th index | |
| #Put model into eval mode, make prediciton | |
| effnetb2.eval() | |
| with torch.inference_mode(): | |
| # Pass the transformed image through the model and turn the prdiciton logits into probability | |
| # pred_logit = effnetb2(transformed_img) | |
| pred_probs = torch.softmax(effnetb2(transformed_img), dim = 1) | |
| # pred_label = torch.argmax(pred_probs, dim = 1) | |
| # class_name = class_names[pred_label] | |
| # 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 = "FoodVision Mini 🍕🥩🍣" | |
| description = "An [EfficientNetB2 feature extractor] (https://pytorch.org/vision/main/models/generated/torchvision.models.efficientnet_b2.html#torchvision.models.efficientnet_b2) computer vision model to classify images as pizza, steak or sushi." | |
| article = "Created at PyTorch Model Deployment" | |
| # 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 = 3, label = "predictions"), | |
| gr.Number(label="Prediciton time (s)")], | |
| examples = example_list, | |
| title = title, | |
| description = description, | |
| article = article | |
| ) | |
| #Launch the demo: | |
| demo.launch() # Don't need share = True in Hugging Face Spaces | |