Spaces:
Sleeping
Sleeping
File size: 2,761 Bytes
3719f7b ddca64b 3719f7b |
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 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
### 1. Imports and class names setup ###
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
# Setup class names
class_names = ["pizza", "steak", "sushi"]
### 2. Model and transforms preparation ###
# Create EffNetB2 model
effnetb2, effnetb2_transforms = create_effnetb2_model(
num_classes=3, # len(class_names) would also work
)
# Load saved weights
effnetb2.load_state_dict(
torch.load(
f="09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth",
map_location=torch.device("cpu"), # load to CPU
)
)
### 3. Predict function ###
# Create predict function
def predict(img) -> Tuple[Dict, float]:
"""Transforms and performs a prediction on img and returns prediction and time taken.
"""
# Start the timer
start_time = timer()
# Transform the target image and add a batch dimension
img = effnetb2_transforms(img).unsqueeze(0)
# Put model into evaluation mode and turn on inference mode
effnetb2.eval()
with torch.inference_mode():
# Pass the transformed image through the model and turn the prediction logits into prediction probabilities
pred_probs = torch.softmax(effnetb2(img), dim=1)
# Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter)
pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
# Calculate the prediction time
pred_time = round(timer() - start_time, 5)
# Return the prediction dictionary and prediction time
return pred_labels_and_probs, pred_time
### 4. Gradio app ###
# Create title, description and article strings
title = "FoodVision Mini 🍕🥩🍣"
description = "An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi."
# Create examples list from "examples/" directory
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)
# Launch the demo!
demo.launch()
|