Spaces:
Sleeping
Sleeping
File size: 1,515 Bytes
5d3d2ca b16bd8f 5d3d2ca c1bf96c 5d3d2ca |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
import os
import torch
import gradio as gr
from model import create_effnetb2_model
from timeit import default_timer as timer
from typing import List, Dict, Tuple
class_names = ["pizza", "steak", "sushi"]
effnetb2, effnetb2_transform = create_effnetb2_model(num_classes=len(class_names))
state_dict = torch.load(
"pretrained_effnetb2_pizza_steak_sushi_20_percent.pt",
map_location=torch.device("cpu") # Load model to the CPU
)
effnetb2.load_state_dict(state_dict)
def predict(img) -> Tuple[Dict, float]:
start_time = timer()
img = effnetb2_transform(img).unsqueeze(0)
effnetb2.eval()
with torch.inference_mode():
pred_probs = torch.softmax(effnetb2(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()
return pred_labels_and_probs, round(end_time-start_time, 4)
title = "FoodVision Mini"
description = "An [EfficientNetB2 feature extractor](www.google.com) computer vision model to classify images as pizza, steak, sushi"
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=3, label="Predictions"),
gr.Number(label="Prediction time (s)")],
examples=example_list,
title=title,
description=description)
demo.launch(debug=False)
|