|
|
|
|
|
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 |
|
|
|
|
|
with open("class_names.txt", "r") as f: |
|
class_names = [food.strip('\n') for food in f.readlines()] |
|
|
|
|
|
effnetb2_food101, effnetb2_transforms = create_effnetb2_model(num_classes = 101) |
|
|
|
|
|
effnetb2_food101.load_state_dict(torch.load("models/state_dict__effnetb2_food101_20_percent.pth", |
|
map_location = torch.device('cpu'))) |
|
|
|
|
|
|
|
def predict(img) -> Tuple[Dict, float]: |
|
|
|
|
|
start_time = timer() |
|
|
|
|
|
img = effnetb2_transforms(img).unsqueeze(0) |
|
|
|
|
|
effnetb2_food101.eval() |
|
with torch.inference_mode(): |
|
|
|
pred_probs = torch.softmax(effnetb2_food101(img), dim = 1) |
|
|
|
|
|
pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))} |
|
|
|
|
|
end_time = timer() |
|
pred_time = round(end_time - start_time, 4) |
|
|
|
|
|
return pred_labels_and_probs, pred_time |
|
|
|
|
|
title = 'FoodIdentifier Big (a little) π£ππ₯©' |
|
description = "An EfficientNetB2 feature extractor computer vision model to classify images as pizza, sushi or steak" |
|
article = " anything I want for the description of the description above π€ͺ" |
|
|
|
|
|
|
|
example_list = [["examples/" + example] for example in os.listdir("examples")] |
|
|
|
|
|
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 = example_list, |
|
title = title, |
|
description = description, |
|
article = article |
|
) |
|
|
|
|
|
demo.launch(debug = False, |
|
share = True) |
|
|