Upload 6 files

app.py

@@ -1,3 +1,5 @@
+def sepia(input_img, intensity):
+
 import gradio as gr
 
 from matplotlib import gridspec
@@ -8,10 +10,10 @@ import tensorflow as tf
 from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
 
 feature_extractor = SegformerFeatureExtractor.from_pretrained(
-    "mattmdjaga/segformer_b2_clothes"
+    "nvidia/segformer-b5-finetuned-cityscapes-1024-1024"
 )
 model = TFSegformerForSemanticSegmentation.from_pretrained(
-    "mattmdjaga/segformer_b2_clothes"
+    "nvidia/segformer-b5-finetuned-cityscapes-1024-1024"
 )
 
 def ade_palette():
@@ -226,17 +228,21 @@ def sepia(input_img):
         color_seg[seg.numpy() == label, :] = color
 
     # Show image + mask
-    pred_img = np.array(input_img) * 0.5 + color_seg * 0.5
+    pred_img = np.array(input_img) * (1 - intensity) + color_seg * intensity
     pred_img = pred_img.astype(np.uint8)
 
     fig = draw_plot(pred_img, seg)
     return fig
 
-demo = gr.Interface(fn=sepia,
-                    inputs=gr.Image(shape=(400, 600)),
-                    outputs=['plot'],
-                    examples=["person-1.jpg", "person-2.jpg", "person-3.jpg", "person-4.jpg", "person-5.jpg"],
-                    allow_flagging='never')
-
 
-demo.launch()
+demo = gr.Interface(
+    fn=sepia,
+    inputs=[gr.inputs.Image(shape=(400, 600)), gr.inputs.Slider(minimum=0, maximum=1, step=0.1, default=0.5)],
+    outputs='plot',
+    examples=[["cheonggyecheon_stream_in_seoul_city.jpg", 0.5], ["Incheon_stadium.jpg", 0.7],
+              ["Incheon_city.jpg", 0.3]],
+    title="Semantic Segmentation",
+    description="This is a demo of semantic segmentation using Segformer.",
+    allow_flagging=False,
+)
+demo.launch()

labels.txt

@@ -1,18 +1,19 @@
-Background
-Hat
-Hair
-Sunglasses
-Upper-clothes
-Skirt
-Pants
-Dress
-Belt
-Left-shoe
-Right-shoe
-Face
-Left-leg
-Right-leg
-Left-arm
-Right-arm
-Bag
-Scarf
+road
+sidewalk
+building
+wall
+fence
+pole
+traffic light
+traffic sign
+vegetation
+terrain
+sky
+person
+rider
+car
+truck
+bus
+train
+motorcycle
+bicycle