| import numpy as np | |
| import gradio as gr | |
| from transformers import AutoImageProcessor, AutoModelForImageClassification | |
| from PIL import Image | |
| import torch | |
| import pandas as pd | |
| processor = AutoImageProcessor.from_pretrained("Moreza009/HF_CVcourse_FoodClassifier") | |
| model = AutoModelForImageClassification.from_pretrained("Moreza009/HF_CVcourse_FoodClassifier") | |
| def classifier(image): | |
| if isinstance(image, np.ndarray): | |
| image = Image.fromarray(image) | |
| #image = Image.open(image) | |
| inputs = processor(images=image, return_tensors="pt") | |
| outputs = model(**inputs) | |
| logits = outputs.logits | |
| probabilities = torch.nn.functional.softmax(logits, dim=-1) | |
| predicted_class_idxs = probabilities.topk(5, dim=-1)[1].tolist()[0] | |
| probabilities = probabilities.tolist()[0][:5] | |
| classes = [model.config.id2label[idx] for idx in predicted_class_idxs] | |
| df = pd.DataFrame({'food':classes , 'posibility': probabilities}) | |
| return df.to_html(index=False) | |
| food = gr.Interface( | |
| fn=classifier, | |
| inputs=gr.Image(type="pil"), | |
| outputs="html", | |
| title = "what's your eating?", | |
| description = " :) " | |
| ) | |
| food.launch() |