city

app.py

@@ -1,10 +1,12 @@
 import gradio as gr
-from PIL import Image
+
+from matplotlib import gridspec
+import matplotlib.pyplot as plt
 import numpy as np
-from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
+from PIL import Image
 import tensorflow as tf
+from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
 
-# Load the Segformer model and feature extractor
 feature_extractor = SegformerFeatureExtractor.from_pretrained(
     "nvidia/segformer-b1-finetuned-cityscapes-1024-1024"
 )
@@ -12,34 +14,6 @@ model = TFSegformerForSemanticSegmentation.from_pretrained(
     "nvidia/segformer-b1-finetuned-cityscapes-1024-1024"
 )
 
-def sepia(image_path):
-    input_img = Image.open(image_path)
-
-    inputs = feature_extractor(images=input_img, return_tensors="tf")
-    outputs = model(**inputs)
-    logits = outputs.logits
-
-    logits = tf.transpose(logits, [0, 2, 3, 1])
-    logits = tf.image.resize(
-        logits, input_img.size[::-1]
-    )
-
-    seg = tf.math.argmax(logits, axis=-1)[0]
-
-    colormap = np.asarray(ade_palette())
-    color_seg = np.zeros(
-        (seg.shape[0], seg.shape[1], 3), dtype=np.uint8
-    )
-
-    for label, color in enumerate(colormap):
-        color_seg[seg.numpy() == label, :] = color
-
-    # Combine original image with segmentation mask
-    pred_img = np.array(input_img) * 0.5 + color_seg * 0.5
-    pred_img = pred_img.astype(np.uint8)
-
-    return pred_img
-
 def ade_palette():
     """ADE20K palette that maps each class to RGB values."""
     return [
@@ -64,10 +38,74 @@ def ade_palette():
         [156, 200, 56]
     ]
 
+labels_list = []
+
+with open(r'labels.txt', 'r') as fp:
+    for line in fp:
+        labels_list.append(line[:-1])
+
+colormap = np.asarray(ade_palette())
+
+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]
+
+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)
+
+    unique_labels = np.unique(seg.numpy().astype("uint8"))
+    ax = plt.subplot(grid_spec[1])
+    plt.imshow(FULL_COLOR_MAP[unique_labels].astype(np.uint8), interpolation="nearest")
+    ax.yaxis.tick_right()
+    plt.yticks(range(len(unique_labels)), LABEL_NAMES[unique_labels])
+    plt.xticks([], [])
+    ax.tick_params(width=0.0, labelsize=25)
+    return fig
+
+def sepia(input_img):
+    input_img = Image.fromarray(input_img)
+
+    inputs = feature_extractor(images=input_img, return_tensors="tf")
+    outputs = model(**inputs)
+    logits = outputs.logits
+
+    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]
+
+    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
+
 demo = gr.Interface(fn=sepia,
-                    inputs=gr.File(type="image"),
-                    outputs=gr.Image(),
+                    inputs=gr.Image(shape=(400, 600)),
+                    outputs=['plot'],
                     examples=["img_1.jpg", "img_2.jpeg", "img_3.jpg", "img_4.jpg", "img_5.png"],
                     allow_flagging='never')
 
+
 demo.launch()