hf_transformers_js/zeroshotimageclassification.html at main · sgheith/hf_transformers_js · GitHub

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
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
<!DOCTYPE html>
<html lang="en">

<head>
    <meta charset="UTF-8">
    <title>Zero Shot Image Classification - Hugging Face Transformers.js</title>

    <script type="module">
        // Import the library
        import { pipeline } from 'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.5.4';

        // Make it available globally
        window.pipeline = pipeline;
    </script>

    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.1.0/dist/css/bootstrap.min.css" rel="stylesheet">

    <link rel="stylesheet" href="css/styles.css">
</head>

<body>
    <div class="container-main">
        <!-- Page Header -->
        <div class="header">
            <div class="header-logo">
                <img src="images/logo.png" alt="logo">
            </div>
            <div class="header-main-text">
                <h1>Hugging Face Transformers.js</h1>
            </div>
            <div class="header-sub-text">
                <h3>Free AI Models for JavaScript Web Development</h3>
            </div>
        </div>
        <hr> <!-- Separator -->

        <!-- Back to Home button -->
        <div class="row mt-5">
            <div class="col-md-12 text-center">
                <a href="index.html" class="btn btn-outline-secondary"
                    style="color: #3c650b; border-color: #3c650b;">Back to Main Page</a>
            </div>
        </div>

        <!-- Content -->
        <div class="container mt-5">
            <!-- Centered Titles -->
            <div class="text-center">
                <h2>Computer Vision</h2>
                <h4>Zero Shot Image Classification</h4>
            </div>

            <!-- Actual Content of this page -->
            <div id="zero-shot-image-classification-container" class="container mt-4">
                <h5>Zero Shot Image Classification w/ Xenova/clip-vit-base-patch32:</h5>
                <div class="d-flex align-items-center mb-2">
                    <label for="zeroShotImageClassificationURLText" class="mb-0 text-nowrap"
                        style="margin-right: 15px;">Enter
                        image URL:</label>
                    <input type="text" class="form-control flex-grow-1" id="zeroShotImageClassificationURLText"
                        value="https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg"
                        placeholder="Enter image" style="margin-right: 15px; margin-left: 15px;">
                </div>
                <div class="d-flex align-items-center">
                    <label for="labelsText" class="mb-0 text-nowrap" style="margin-right: 15px;">Enter Labels (comma
                        separated):</label>
                    <input type="text" class="form-control flex-grow-1" id="labelsText" value="tiger, horse, dog"
                        placeholder="Enter labels (comma separated)" style="margin-right: 15px; margin-left: 15px;">
                    <button id="classifyButton" class="btn btn-primary ml-2" onclick="classifyImage()">Classify</button>
                </div>
                <div class="mt-4">
                    <h4>Output:</h4>
                    <pre id="outputArea"></pre>
                </div>
            </div>

            <hr> <!-- Line Separator -->

            <div id="zero-shot-image-classification-local-container" class="container mt-4">
                <h5>Zero Shot Image Classification Local File:</h5>
                <div class="d-flex align-items-center mb-2">
                    <label for="imageClassificationLocalFile" class="mb-0 text-nowrap"
                        style="margin-right: 15px;">Select Local Image:</label>
                    <input type="file" id="imageClassificationLocalFile" accept="image/*" />
                </div>
                <div class="d-flex align-items-center">
                    <label for="labelsLocalText" class="mb-0 text-nowrap" style="margin-right: 15px;">Enter Labels (comma
                        separated):</label>
                    <input type="text" class="form-control flex-grow-1" id="labelsLocalText" value="tiger, horse, dog"
                        placeholder="Enter labels (comma separated)" style="margin-right: 15px; margin-left: 15px;">
                    <button id="classifyLocalButton" class="btn btn-primary ml-2" onclick="classifyLocalImage()">Classify</button>
                </div>
                <div class="mt-4">
                    <h4>Output:</h4>
                    <pre id="outputAreaLocal"></pre>
                </div>
            </div>

        </div>

        <!-- Back to Home button -->
        <div class="row mt-5">
            <div class="col-md-12 text-center">
                <a href="index.html" class="btn btn-outline-secondary"
                    style="color: #3c650b; border-color: #3c650b;">Back to Main Page</a>
            </div>
        </div>
    </div>
    </div>

    <script>

        let classifier;

        // Initialize the sentiment analysis model
        async function initializeModel() {
            classifier = await pipeline('zero-shot-image-classification', 'Xenova/clip-vit-base-patch32');

        }

        async function classifyImage() {
            const textFieldValue = document.getElementById("zeroShotImageClassificationURLText").value.trim();
            const labels = document.getElementById("labelsText").value.trim().split(",").map(item => item.trim());

            const result = await classifier(textFieldValue, labels);

            document.getElementById("outputArea").innerText = JSON.stringify(result, null, 2);
        }

        async function classifyLocalImage() {
            const fileInput = document.getElementById("imageClassificationLocalFile");
            const file = fileInput.files[0];

            if (!file) {
                alert('Please select an image file first.');
                return;
            }

            // Create a Blob URL from the file
            const url = URL.createObjectURL(file);
            const labels = document.getElementById("labelsLocalText").value.trim().split(",").map(item => item.trim());

            const result = await classifier(url, labels);

            document.getElementById("outputAreaLocal").innerText = JSON.stringify(result, null, 2);
        }

        // Initialize the model after the DOM is completely loaded
        window.addEventListener("DOMContentLoaded", initializeModel);
    </script>
</body>

</html>