File size: 8,284 Bytes
f6ed594 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 |
import streamlit as st
# Custom CSS for better styling
st.markdown("""
<style>
.main-title {
font-size: 36px;
color: #4A90E2;
font-weight: bold;
text-align: center;
}
.sub-title {
font-size: 24px;
color: #4A90E2;
margin-top: 20px;
}
.section {
background-color: #f9f9f9;
padding: 15px;
border-radius: 10px;
margin-top: 20px;
}
.section h2 {
font-size: 22px;
color: #4A90E2;
}
.section p, .section ul {
color: #666666;
}
.link {
color: #4A90E2;
text-decoration: none;
}
.benchmark-table {
width: 100%;
border-collapse: collapse;
margin-top: 20px;
}
.benchmark-table th, .benchmark-table td {
border: 1px solid #ddd;
padding: 8px;
text-align: left;
}
.benchmark-table th {
background-color: #4A90E2;
color: white;
}
.benchmark-table td {
background-color: #f2f2f2;
}
</style>
""", unsafe_allow_html=True)
# Main Title
st.markdown('<div class="main-title">Image Zero Shot Classification with CLIP</div>', unsafe_allow_html=True)
# Description
st.markdown("""
<div class="section">
<p><strong>CLIP (Contrastive Language-Image Pre-Training)</strong> is a neural network trained on image and text pairs. It has the capability to classify images without requiring hard-coded labels, making it highly flexible. Labels can be provided during inference, similar to the zero-shot capabilities of GPT-2 and GPT-3 models.</p>
<p>This model was imported from Hugging Face Transformers: <a class="link" href="https://huggingface.co/openai/clip-vit-base-patch32" target="_blank">CLIP Model on Hugging Face</a></p>
</div>
""", unsafe_allow_html=True)
# How to Use
st.markdown('<div class="sub-title">How to Use the Model</div>', unsafe_allow_html=True)
st.code('''
import sparknlp
from sparknlp.base import *
from sparknlp.annotator import *
from pyspark.ml import Pipeline
# Load image data
imageDF = spark.read \\
.format("image") \\
.option("dropInvalid", value = True) \\
.load("src/test/resources/image/")
# Define Image Assembler
imageAssembler: ImageAssembler = ImageAssembler() \\
.setInputCol("image") \\
.setOutputCol("image_assembler")
# Define candidate labels
candidateLabels = [
"a photo of a bird",
"a photo of a cat",
"a photo of a dog",
"a photo of a hen",
"a photo of a hippo",
"a photo of a room",
"a photo of a tractor",
"a photo of an ostrich",
"a photo of an ox"]
# Define CLIP classifier
imageClassifier = CLIPForZeroShotClassification \\
.pretrained() \\
.setInputCols(["image_assembler"]) \\
.setOutputCol("label") \\
.setCandidateLabels(candidateLabels)
# Create pipeline
pipeline = Pipeline().setStages([imageAssembler, imageClassifier])
# Apply pipeline to image data
pipelineDF = pipeline.fit(imageDF).transform(imageDF)
# Show results
pipelineDF \\
.selectExpr("reverse(split(image.origin, '/'))[0] as image_name", "label.result") \\
.show(truncate=False)
''', language='python')
# Results
st.markdown('<div class="sub-title">Results</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
<table class="benchmark-table">
<tr>
<th>Image Name</th>
<th>Result</th>
</tr>
<tr>
<td>palace.JPEG</td>
<td>[a photo of a room]</td>
</tr>
<tr>
<td>egyptian_cat.jpeg</td>
<td>[a photo of a cat]</td>
</tr>
<tr>
<td>hippopotamus.JPEG</td>
<td>[a photo of a hippo]</td>
</tr>
<tr>
<td>hen.JPEG</td>
<td>[a photo of a hen]</td>
</tr>
<tr>
<td>ostrich.JPEG</td>
<td>[a photo of an ostrich]</td>
</tr>
<tr>
<td>junco.JPEG</td>
<td>[a photo of a bird]</td>
</tr>
<tr>
<td>bluetick.jpg</td>
<td>[a photo of a dog]</td>
</tr>
<tr>
<td>chihuahua.jpg</td>
<td>[a photo of a dog]</td>
</tr>
<tr>
<td>tractor.JPEG</td>
<td>[a photo of a tractor]</td>
</tr>
<tr>
<td>ox.JPEG</td>
<td>[a photo of an ox]</td>
</tr>
</table>
</div>
""", unsafe_allow_html=True)
# Model Information
st.markdown('<div class="sub-title">Model Information</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
<table class="benchmark-table">
<tr>
<th>Attribute</th>
<th>Description</th>
</tr>
<tr>
<td><strong>Model Name</strong></td>
<td>zero_shot_classifier_clip_vit_base_patch32</td>
</tr>
<tr>
<td><strong>Compatibility</strong></td>
<td>Spark NLP 5.2.0+</td>
</tr>
<tr>
<td><strong>License</strong></td>
<td>Open Source</td>
</tr>
<tr>
<td><strong>Edition</strong></td>
<td>Official</td>
</tr>
<tr>
<td><strong>Input Labels</strong></td>
<td>[image_assembler]</td>
</tr>
<tr>
<td><strong>Output Labels</strong></td>
<td>[classification]</td>
</tr>
<tr>
<td><strong>Language</strong></td>
<td>en</td>
</tr>
<tr>
<td><strong>Size</strong></td>
<td>392.8 MB</td>
</tr>
</table>
</div>
""", unsafe_allow_html=True)
# Data Source Section
st.markdown('<div class="sub-title">Data Source</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
<p>The CLIP model is available on <a class="link" href="https://huggingface.co/openai/clip-vit-base-patch32" target="_blank">Hugging Face</a>. This model was trained on image-text pairs and can be used for zero-shot image classification.</p>
</div>
""", unsafe_allow_html=True)
# References
st.markdown('<div class="sub-title">References</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
<ul>
<li><a class="link" href="https://sparknlp.org/2023/12/02/zero_shot_classifier_clip_vit_base_patch32_en.html" target="_blank" rel="noopener">CLIP Model on Spark NLP</a></li>
<li><a class="link" href="https://huggingface.co/openai/clip-vit-base-patch32" target="_blank" rel="noopener">CLIP Model on Hugging Face</a></li>
<li><a class="link" href="https://github.com/openai/CLIP" target="_blank" rel="noopener">CLIP GitHub Repository</a></li>
<li><a class="link" href="https://arxiv.org/abs/2103.00020" target="_blank" rel="noopener">CLIP Paper</a></li>
</ul>
</div>
""", unsafe_allow_html=True)
# Community & Support
st.markdown('<div class="sub-title">Community & Support</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
<ul>
<li><a class="link" href="https://sparknlp.org/" target="_blank">Official Website</a>: Documentation and examples</li>
<li><a class="link" href="https://join.slack.com/t/spark-nlp/shared_invite/zt-198dipu77-L3UWNe_AJ8xqDk0ivmih5Q" target="_blank">Slack</a>: Live discussion with the community and team</li>
<li><a class="link" href="https://github.com/JohnSnowLabs/spark-nlp" target="_blank">GitHub</a>: Bug reports, feature requests, and contributions</li>
<li><a class="link" href="https://medium.com/spark-nlp" target="_blank">Medium</a>: Spark NLP articles</li>
<li><a class="link" href="https://www.youtube.com/channel/UCmFOjlpYEhxf_wJUDuz6xxQ/videos" target="_blank">YouTube</a>: Video tutorials</li>
</ul>
</div>
""", unsafe_allow_html=True)
|