File size: 2,532 Bytes
a251afc
 
bf65937
a251afc
 
 
 
bf65937
 
a251afc
 
 
 
 
 
 
 
 
 
 
 
 
 
972a2b8
a251afc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
77
78
79
80
### 1. Imports and class names setup ### 
import os
import gradio as gr
import torch
from timeit import default_timer as timer
from typing import Tuple, Dict

from model import create_effnetb2_model

# Setup class names
with open("class_names.txt", "r") as f: # reading them in from class_names.txt
    class_names = [food_name.strip() for food_name in  f.readlines()]
    
### 2. Model and transforms preparation ###    

# Create model
effnetb2, effnetb2_transforms = create_effnetb2_model(
    num_classes=len(class_names),
)

# Load saved weights
effnetb2.load_state_dict(
    torch.load(
        f="models/pretrained_effnetb2_feature_extractor_food101_100_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 = "Lens 📷"
description = "An EfficientNetB2 feature extractor computer vision model to classify images of food into 101 different classes"

# Create examples list from "examples/" directory
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,
)

# Launch the app!
demo.launch()