Initial commit.

app.py

@@ -13,6 +13,7 @@ from torchvision import transforms
 # WEIGHTS = './weights/segmenter.pth
 WEIGHTS = './weights/segmenter_nusc.pth'
 FULL = True
+CACHE = False
 ALPHA = 0.5
 
 
@@ -170,10 +171,10 @@ def predict(input_img):
     return drawing_blend_pseudo, drawing_blend_cs
 
 
-title = "Drive&Segment"
+title = '<h1 align="center">Drive&Segment</h1>'
 description = 'Gradio Demo accompanying paper "Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation"\nBecause of the CPU-only inference, it might take up to 20s for large images.\nRight now, it uses the Segmenter model trained on nuScenes and with a simplified inference scheme (for the sake of speed).'
 # article = "<p style='text-align: center'><a href='https://vobecant.github.io/DriveAndSegment/' target='_blank'>Project Page</a> | <a href='https://github.com/vobecant/DriveAndSegment' target='_blank'>Github</a></p>"
-article="""
+article = """
 <h1 align="center">🚙📷 Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation</h1>
 
 <h2 align="center">
@@ -202,21 +203,21 @@ the raw non-curated data collected by cars which, equipped with 📷 cameras and
 
 Example of **pseudo** segmentation.
 
-![](https://github.com/vobecant/DriveAndSegment/blob/main/sources/video128_blend03_v2_10fps_640px_lanczos.gif)
+![](https://drive.google.com/uc?export=view&id=1xB_JdIL2bC6ka2hbs0wgXYtLpb1r07hw)
 
 ### Cityscapes segmentation.
 
 Two examples of pseudo segmentation mapped to the 19 ground-truth classes of the Cityscapes dataset by using Hungarian
 algorithm.
 
-![](https://github.com/vobecant/DriveAndSegment/blob/main/sources/video_stuttgart00_remap_blended03_20fps_crop.gif)
-![](https://github.com/vobecant/DriveAndSegment/blob/main/sources/video_stuttgart01_remap_blended03_20fps_crop2.gif)
+![](https://drive.google.com/uc?export=view&id=1vHF2DugjXr4FdXX3gW65GRPArNL5urEH)
+![](https://drive.google.com/uc?export=view&id=1WI_5lmF_YoVFXdWDnPT29rhPnlylh7QV)
 """
-examples = [ #'examples/img5.jpeg',
-            'examples/100.jpeg',
-            'examples/39076.jpeg',
-            'examples/img1.jpg',
-            'examples/snow1.jpg']
+examples = [  # 'examples/img5.jpeg',
+    'examples/100.jpeg',
+    'examples/39076.jpeg',
+    'examples/img1.jpg',
+    'examples/snow1.jpg']
 examples += ['examples/cs{}.jpg'.format(i) for i in range(2, 5)]
 
 # predict(examples[0])
@@ -231,4 +232,4 @@ iface = gr.Interface(predict, inputs=gr.inputs.Image(type='filepath'), title=tit
 #                      examples=examples)
 
 # iface.launch(show_error=True, share=True)
-iface.launch(enable_queue=True, cache_examples=FULL)
+iface.launch(enable_queue=True, cache_examples=CACHE)