Spaces:
Sleeping
Sleeping
File size: 1,780 Bytes
ca502de |
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 51 52 53 54 55 56 57 58 59 60 61 |
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_name.strip() for food_name in f]
effnetb2, effnetb2_transforms = create_effnetb2_model()
effnetb2.load_state_dict(
torch.load(
f="effnetb2_food101_complete_dataset.pth",
map_location=torch.device("cpu"),
weights_only=True
)
)
def predict(img) -> Tuple[Dict, float]:
start_time = timer()
img = effnetb2_transforms(img).unsqueeze(0)
effnetb2.eval()
with torch.inference_mode():
pred_probs = torch.softmax(effnetb2(img), dim=1)
# create a prediction label in gradio format
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)
return pred_labels_and_probs, pred_time
# Create title, description and article strings
title = "FoodVision Big 🍔👁"
description = "An EfficientNetB2 feature extractor computer vision model to classify images of food into [101 different classes](https://github.com/Victoran0/foodvision-bigdataset/demos/foodvision_big/class_names.txt).."
article = "You can find the full source code at (https://github.com/Victoran0/foodvision-bigdataset)."
example_list = [["examples/" + example] for example in os.listdir("examples")]
# Create Gradio Interface
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()
|