Update app.py

app.py

@@ -1,26 +1,80 @@
 import gradio as gr
-from PIL import Image
+
+from matplotlib import gridspec
+import matplotlib.pyplot as plt
 import numpy as np
+from PIL import Image
 import tensorflow as tf
-from transformers import AutoFeatureExtractor, TFAutoModelForSemanticSegmentation
+from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
 
-# Hugging Face 모델 및 토크나이저
-model_name = "nvidia/segformer-b0-finetuned-cityscapes-1024-1024"
-feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
-model = TFAutoModelForSemanticSegmentation.from_pretrained(model_name)
+feature_extractor = SegformerFeatureExtractor.from_pretrained(
+    "nvidia/segformer-b0-finetuned-cityscapes-1024-1024"
+)
+model = TFSegformerForSemanticSegmentation.from_pretrained(
+    "nvidia/segformer-b0-finetuned-cityscapes-1024-1024"
+)
 
-def label_to_color_image(label, colormap):
-    color_seg = np.zeros(
-        (label.shape[0], label.shape[1], 3), dtype=np.uint8
-    )  # height, width, 3
-    for i in range(len(colormap)):
-        color_seg[label.numpy() == i, :] = colormap[i]
-    return color_seg
+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],
+        [165, 102, 255],
+        [217, 65, 197],
+        [116, 116, 116],
+        [204, 114, 61],
+        [206, 242, 121],
+        [61, 183, 204],
+        [94, 94, 94],
+        [196, 183, 59],
+        [246, 246, 246],
+        [209, 178, 255],
+        [0, 87, 102],
+        [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())
 
-def draw_plot(pred_img, seg, colormap, labels_list):
-    # your existing draw_plot function, unchanged
+def label_to_color_image(label):
+    if label.ndim != 2:
+        raise ValueError("Expect 2-D input label")
 
-def huggingface_model(input_img):
+    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")
@@ -33,48 +87,24 @@ def huggingface_model(input_img):
     )  # We reverse the shape of `image` because `image.size` returns width and height.
     seg = tf.math.argmax(logits, axis=-1)[0]
 
-    # Define the colormap for the cityscapes dataset
-    colormap = [
-        [128, 64, 128],
-        [244, 35, 232],
-        [70, 70, 70],
-        [102, 102, 156],
-        [190, 153, 153],
-        [153, 153, 153],
-        [250, 170, 30],
-        [220, 220, 0],
-        [107, 142, 35],
-        [152, 251, 152],
-        [0, 130, 180],
-        [220, 20, 60],
-        [255, 0, 0],
-        [0, 0, 142],
-        [0, 0, 70],
-        [0, 60, 100],
-        [0, 80, 100],
-        [0, 0, 230],
-        [119, 11, 32],
-    ]
-
-    color_seg = label_to_color_image(seg, colormap)
+    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)
 
-    # Draw plot
-    fig = draw_plot(pred_img, seg, colormap, labels_list)
+    fig = draw_plot(pred_img, seg)
     return fig
 
-# 여러분이 가진 labels.txt 파일의 내용을 labels_list에 할당하세요.
-labels_list = ["label1", "label2", ...]
+demo = gr.Interface(fn=sepia,
+                    inputs=gr.Image(shape=(400, 600)),
+                    outputs=['plot'],
+                    examples=["citiscpae-1.jpg", "citiscape-2.jpg"],
+                    allow_flagging='never')
 
-demo = gr.Interface(
-    fn=huggingface_model,
-    inputs=gr.Image(shape=(1024, 1024)),  # 입력 이미지 크기는 모델의 입력 크기에 맞게 조절해야 합니다.
-    outputs=["plot"],
-    examples=["person-1.jpg", "person-2.jpg", "person-3.jpg", "person-4.jpg", "person-5.jpg"],
-    allow_flagging='never'
-)
 
 demo.launch()