7th

README.md

@@ -4,7 +4,7 @@ emoji: 👁
 colorFrom: green
 colorTo: pink
 sdk: gradio
-sdk_version: 4.2.0
+sdk_version: 3.44.4
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,191 @@
+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
+
+feature_extractor = SegformerFeatureExtractor.from_pretrained(
+    "nvidia/segformer-b3-finetuned-cityscapes-1024-1024"
+)
+model = TFSegformerForSemanticSegmentation.from_pretrained(
+    "nvidia/segformer-b3-finetuned-cityscapes-1024-1024"
+)
+
+def ade_palette():
+    """ADE20K palette that maps each class to RGB values."""
+    return [
+        [255, 0, 0],
+        [255, 94, 0],
+        [255, 187, 0],
+        [255, 228, 0],
+        [171, 242, 0],
+        [29, 219, 22],
+        [0, 216, 255],
+        [0, 84, 255],
+        [1, 0, 255],
+        [95, 0, 255],
+        [255, 0, 221],
+        [255, 0, 127],
+        [0, 0, 0],
+        [255, 255, 255],
+        [255, 216, 216],
+        [250, 224, 212],
+        [250, 236, 197],
+        [250, 244, 192],
+        [228, 247, 186],
+        [206, 251, 201],
+        [212, 244, 250],
+        [217, 229, 255],
+        [218, 217, 255],
+        [232, 217, 255],
+        [255, 217, 250],
+        [255, 217, 236],
+        [246, 246, 246],
+        [234, 234, 234],
+        [255, 167, 167],
+        [255, 193, 158],
+        [255, 224, 140],
+        [250, 237, 125],
+        [206, 242, 121],
+        [183, 240, 177],
+        [178, 235, 244],
+        [178, 204, 255],
+        [181, 178, 255],
+        [209, 178, 255],
+        [255, 178, 245],
+        [255, 178, 217],
+        [213, 213, 213],
+        [189, 189, 189],
+        [241, 95, 95],
+        [242, 150, 97],
+        [242, 203, 97],
+        [229, 216, 92],
+        [188, 229, 92],
+        [134, 229, 127],
+        [92, 209, 229],
+        [103, 153, 255],
+        [107, 102, 255],
+        [165, 102, 255],
+        [243, 97, 220],
+        [243, 97, 166],
+        [166, 166, 166],
+        [140, 140, 140],
+        [93, 93, 93],
+        [116, 116, 116],
+        [217, 65, 140],
+        [217, 65, 197],
+        [128, 65, 217],
+        [70, 65, 217],
+        [67, 116, 217],
+        [61, 183, 204],
+        [71, 200, 62],
+        [159, 201, 60],
+        [196, 183, 59],
+        [204, 166, 61],
+        [204, 114, 61],
+        [204, 61, 61],
+        [152, 0, 0],
+        [153, 56, 0],
+        [153, 112, 0],
+        [153, 138, 0],
+        [107, 153, 0],
+        [47, 157, 39],
+        [0, 130, 153],
+        [0, 51, 153],
+        [5, 0, 153],
+        [63, 0, 153],
+        [153, 0, 133],
+        [153, 0, 76],
+        [76, 76, 76],
+        [53, 53, 53],
+        [25, 25, 25],
+        [33, 33, 33],
+        [102, 0, 51],
+        [102, 0, 88],
+        [42, 0, 102],
+        [3, 0, 102],
+        [0, 34, 102],
+        [0, 87, 102],
+        [34, 116, 28],
+        [71, 102, 0],
+        [102, 92, 0],
+        [102, 75, 0],
+        [102, 37, 0],
+        [103, 0, 0]
+
+    ]
+
+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.Image(shape=(400, 600)),
+                    outputs=['plot'],
+                    examples=["cityscape-1.jpg", "cityscape-2.jpg", "cityscape-3.jpg"],
+                    allow_flagging='never')
+
+
+demo.launch()

labels.txt

@@ -0,0 +1,19 @@
+road
+sidewalk
+building
+wall
+fence
+pole
+traffic light
+traffic sign
+vegetation
+terrain
+sky
+person
+rider
+car
+truck
+bus
+train
+motorcycle
+bicycle

requirements.txt

@@ -0,0 +1,8 @@
+torch
+transformers~=4.35.0
+tensorflow~=2.14.0
+numpy~=1.26.1
+Image
+matplotlib~=3.8.1
+gradio~=4.2.0
+Pillow~=10.1.0