foodvision_mini / app.py
KajetanFrackowiak's picture
Upload app.py
d85f54c verified
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
class_names = ["pizza", "steak", "sushi"]
effnetb2, effnetb2_transforms = create_effnetb2_model(
num_classes=3
)
effnetb2.load_state_dict(
torch.load(
f="09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth",
map_location=torch.device("cpu")
)
)
def predict(img) -> Tuple[Dict, float]:
"""Transforms and performs a prediction on img and returns prediction and time taken."""
start_time = timer()
img = effnetb2_transforms(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))}
pred_time = round(timer() - start_time, 5)
return pred_labels_and_probs, pred_time
title = "FoodVision Mini 🍕🥩🍣"
description = "An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi."
article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)."
example_list = [["examples/" + example] for example in os.listdir("examples")]
# Create the Gradio demo
demo = gr.Interface(fn=predict, # mapping function from input to output
inputs=gr.Image(type="pil"), # what are the inputs?
outputs=[gr.Label(num_top_classes=3, label="Predictions"), # what are the outputs?
gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs
# Create examples list from "examples/" directory
examples=example_list,
title=title,
description=description,
article=article)
# Launch the demo!
demo.launch() # Don't need share=True in Hugging Face spaces