Spaces:
Runtime error
Runtime error
Update description
Browse files
app.py
CHANGED
|
@@ -235,6 +235,8 @@ This is a demo of <a href="https://lukemelas.github.io/deep-spectral-segmentatio
|
|
| 235 |
Our method decomposes an image into a set of soft segments in a <em>completely unsupervised</em> manner. Specifically, we extract the Laplacian eigenvectors of a feature affinity matrix from a large self-supervised network, and we find that we find that these eigenvectors can be readily used to localize and segment objects.
|
| 236 |
|
| 237 |
Below, you can upload an image (or select one of the examples) and see how our method decomposes it into soft segments. Hopefully it will localize some of the objects or semantic segments in your image!
|
|
|
|
|
|
|
| 238 |
"""
|
| 239 |
|
| 240 |
thumbnail = "https://raw.githubusercontent.com/gradio-app/hub-echonet/master/thumbnail.png"
|
| 235 |
Our method decomposes an image into a set of soft segments in a <em>completely unsupervised</em> manner. Specifically, we extract the Laplacian eigenvectors of a feature affinity matrix from a large self-supervised network, and we find that we find that these eigenvectors can be readily used to localize and segment objects.
|
| 236 |
|
| 237 |
Below, you can upload an image (or select one of the examples) and see how our method decomposes it into soft segments. Hopefully it will localize some of the objects or semantic segments in your image!
|
| 238 |
+
|
| 239 |
+
<em>Note: Due to memory constraints on Huggingface, we have to resize the image to a maximum size length of 512px after upload. For best-quality results at full resolution, use our <a href="https://github.com/lukemelas/deep-spectral-segmentation/">GitHub repository</a>.</em>
|
| 240 |
"""
|
| 241 |
|
| 242 |
thumbnail = "https://raw.githubusercontent.com/gradio-app/hub-echonet/master/thumbnail.png"
|