Update app.py

app.py

@@ -1,28 +1,30 @@
 import gradio as gr
-
-from matplotlib import gridspec
-import matplotlib.pyplot as plt
 import numpy as np
-from PIL import Image
 import tensorflow as tf
-from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
+from PIL import Image
+from transformers import SegformerImageProcessor, TFSegformerForSemanticSegmentation
+import matplotlib.pyplot as plt
+from matplotlib import gridspec
 
-feature_extractor = SegformerFeatureExtractor.from_pretrained(
-    "nvidia/segformer-b0-finetuned-cityscapes-1024-1024"
-)
-model = TFSegformerForSemanticSegmentation.from_pretrained(
-    "nvidia/segformer-b0-finetuned-cityscapes-1024-1024"
-)
+# Load model and feature extractor
+feature_extractor = SegformerImageProcessor.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-1024-1024")
+model = TFSegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-1024-1024")
 
+# Load labels
+labels_list = []
+with open(r'labels.txt', 'r') as fp:
+    for line in fp:
+        labels_list.append(line[:-1])
+
+# ADE20K palette
 def ade_palette():
-    """ADE20K palette that maps each class to RGB values."""
     return [
         [255, 0, 0],
         [255, 187, 0],
         [255, 228, 0],
         [29, 219, 22],
         [178, 204, 255],
-        [1, 0, 255],
+        [1, 0, 255], 
         [165, 102, 255],
         [217, 65, 197],
         [116, 116, 116],
@@ -37,30 +39,25 @@ def ade_palette():
         [153, 0, 76]
     ]
 
-labels_list = []
-
-with open(r'labels.txt', 'r') as fp:
-    for line in fp:
-        labels_list.append(line[:-1])
-
 colormap = np.asarray(ade_palette())
 
+# Label to color image mapping
 def label_to_color_image(label):
     if label.ndim != 2:
         raise ValueError("Expect 2-D input label")
-
     if np.max(label) >= len(colormap):
         raise ValueError("label value too large.")
     return colormap[label]
 
+# Draw segmentation plot
 def draw_plot(pred_img, seg):
     fig = plt.figure(figsize=(20, 15))
-
     grid_spec = gridspec.GridSpec(1, 2, width_ratios=[6, 1])
 
     plt.subplot(grid_spec[0])
     plt.imshow(pred_img)
     plt.axis('off')
+
     LABEL_NAMES = np.asarray(labels_list)
     FULL_LABEL_MAP = np.arange(len(LABEL_NAMES)).reshape(len(LABEL_NAMES), 1)
     FULL_COLOR_MAP = label_to_color_image(FULL_LABEL_MAP)
@@ -74,6 +71,7 @@ def draw_plot(pred_img, seg):
     ax.tick_params(width=0.0, labelsize=25)
     return fig
 
+# Sepia function
 def sepia(input_img):
     input_img = Image.fromarray(input_img)
 
@@ -84,27 +82,28 @@ def sepia(input_img):
     logits = tf.transpose(logits, [0, 2, 3, 1])
     logits = tf.image.resize(
         logits, input_img.size[::-1]
-    )  # We reverse the shape of `image` because `image.size` returns width and height.
-    seg = tf.math.argmax(logits, axis=-1)[0]
+    )
 
+    seg = tf.math.argmax(logits, axis=-1)[0]
     color_seg = np.zeros(
         (seg.shape[0], seg.shape[1], 3), dtype=np.uint8
-    )  # height, width, 3
+    )
+
     for label, color in enumerate(colormap):
         color_seg[seg.numpy() == label, :] = color
 
-    # Show image + mask
     pred_img = np.array(input_img) * 0.5 + color_seg * 0.5
     pred_img = pred_img.astype(np.uint8)
 
     fig = draw_plot(pred_img, seg)
     return fig
 
+# Gradio Interface
 demo = gr.Interface(fn=sepia,
                     inputs=gr.Image(shape=(800, 1200)),
                     outputs=['plot'],
                     examples=["citiscape-1.jpg", "citiscape-2.jpg"],
                     allow_flagging='never')
 
-
+# Launch the interface
 demo.launch()