update

app.py

@@ -25,8 +25,11 @@ if torch.cuda.is_available():
     torch.backends.cudnn.deterministic = True
 
 # Device
-DEVICE = "cpu"
-print(DEVICE)
+# Use GPU if available
+if torch.cuda.is_available():
+    DEVICE = torch.device("cuda")
+else:
+    DEVICE = torch.device("cpu")
 
 # Make directories
 os.system("mkdir ./models")
@@ -78,7 +81,22 @@ inputs = gr.inputs.Image(type="filepath", label="Input Image")
 
 # Define style
 title = "Learning to Recognize Occluded and Small Objects with Partial Inputs"
-description = "TBA."
+description = """
+Try this demo for <a href="https://github.com/hasibzunair/msl-recognition">MSL</a>,
+introduced in <a href="ADD_PAPER_LINK">Learning to Recognize Occluded and Small Objects with Partial Inputs</a>.
+\n\n MSL aims to explicitly focus on context from neighbouring regions around 
+objects. Further, this also enables to learn a distribution of association across classes. Ideally to handle situations in-the-wild where only part of some object class is visible, but where us humans might readily use context to infer the classes presence.
+
+You can use this demo to get the a list of objects present in your images.
+
+To use it, simply upload an image of your choice and hit submit. You will get one or more names of objects present
+in your images from this list: ("aeroplane", "bicycle", "bird", "boat", "bottle",
+           "bus", "car", "cat", "chair", "cow", "diningtable",
+           "dog", "horse", "motorbike", "person", "pottedplant",
+           "sheep", "sofa", "train", "tvmonitor")
+
+\n\n<a href="https://hasibzunair.github.io/msl-recognition/">Project Page</a>
+"""
 article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1512.03385' target='_blank'>Learning to Recognize Occluded and Small Objects with Partial Inputs</a> | <a href='https://github.com/hasibzunair/msl-recognition' target='_blank'>Github Repo</a></p>"
 
 voc_classes = ("aeroplane", "bicycle", "bird", "boat", "bottle",