finish

app.py

@@ -58,14 +58,27 @@ def label_to_color_image(label):
     return colormap[label]
 
 
-def draw_class_visualization(seg, class_id):
-    class_mask = seg.numpy() == class_id
-    class_color = colormap[class_id]
+def draw_plot(pred_img, seg):
+    fig = plt.figure(figsize=(20, 15))
 
-    class_visualization = np.zeros(seg.shape + (3,))
-    class_visualization[class_mask] = class_color
+    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
 
-    return class_visualization
 
 def sepia(input_img):
     input_img = Image.fromarray(input_img)
@@ -73,35 +86,29 @@ def sepia(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]
 
-    class_visualizations = []
-    for class_id in range(len(colormap)):
-        class_visualization = draw_class_visualization(seg, class_id)
-        class_visualizations.append(class_visualization)
-
-    return class_visualizations
-
+    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
 
-def plot_class_visualization(class_visualizations):
-    fig, axes = plt.subplots(1, len(class_visualizations), figsize=(20, 15))
+    # Show image + mask
+    pred_img = np.array(input_img) * 0.5 + color_seg * 0.5
+    pred_img = pred_img.astype(np.uint8)
 
-    for i, class_visualization in enumerate(class_visualizations):
-        ax = axes[i]
-        ax.imshow(class_visualization)
-        ax.axis('off')
-        ax.set_title(labels_list[i])
-        return fig
+    fig = draw_plot(pred_img, seg)
+    return fig
 
 
 demo = gr.Interface(fn=sepia,
                     inputs=gr.Image(shape=(1024, 1024)),
-                    outputs=gr.outputs.Image(type='plot', label="Class Visualizations"),
+                    outputs=['plot'],
                     examples=["city-1.jpg", "city-2.jpg", "city-3.jpg", "city-4.jpg", "city-5.jpg"],
                     allow_flagging='never')