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-b0-finetuned-ade-512-512" ) model = TFSegformerForSemanticSegmentation.from_pretrained( "nvidia/segformer-b0-finetuned-ade-512-512" ) def ade_palette(): """ADE20K palette that maps each class to RGB values.""" return [ [22, 122, 213], [240, 3, 156], [87, 176, 33], [154, 88, 111], [63, 54, 244], [201, 235, 59], [102, 66, 183], [94, 147, 5], [39, 198, 247], [17, 149, 92], [130, 78, 184], [246, 119, 107], [225, 23, 68], [52, 189, 140], [142, 10, 22], [114, 161, 251], [168, 55, 34], [75, 203, 89], [32, 45, 235], [217, 134, 0], [186, 98, 150], [123, 205, 17], [58, 29, 192], [159, 171, 60], [107, 240, 218], [4, 80, 124], [195, 146, 215], [85, 39, 10], [137, 112, 160], [247, 26, 82], [216, 210, 115], [48, 135, 229], [165, 183, 43], [74, 1, 129], [31, 166, 96], [223, 51, 202], [57, 72, 27], [143, 191, 176], [111, 33, 244], [20, 155, 62], [128, 99, 209], [254, 120, 14], [229, 67, 175], [53, 206, 40], [140, 16, 111], [95, 180, 237], [38, 58, 152], [116, 214, 81], [171, 47, 23], [209, 36, 178], [25, 119, 74], [147, 232, 93], [61, 153, 255], [198, 77, 10], [8, 166, 142], [133, 45, 111], [222, 199, 239], [56, 18, 90], [164, 98, 206], [239, 135, 60], [106, 28, 139], [49, 172, 224], [179, 109, 34], [12, 191, 157], [121, 64, 88], [243, 214, 127], [82, 11, 165], [158, 37, 192], [31, 144, 55], [176, 220, 252], [68, 5, 123], [220, 157, 73], [41, 183, 210], [173, 85, 14], [16, 131, 99], [135, 50, 177], [227, 202, 244], [54, 21, 115], [162, 101, 231], [236, 138, 49], [103, 31, 146], [47, 175, 217], [181, 112, 28], [15, 190, 160], [124, 66, 91], [241, 217, 130], [80, 13, 168], [157, 40, 195], [30, 147, 52], [175, 223, 249], [67, 7, 126], [218, 160, 76], [44, 180, 213], [172, 83, 19], [19, 129, 102], [136, 53, 174], [226, 205, 241], [52, 24, 118], [160, 104, 228], [235, 141, 45], [101, 33, 149], [46, 178, 220], [182, 114, 31], [14, 193, 163], [122, 69, 94], [240, 219, 133], [79, 16, 171], [156, 43, 198], [29, 150, 58], [174, 225, 246], [66, 9, 129], [217, 163, 79], [43, 182, 216], [171, 81, 22], [21, 128, 105], [137, 56, 176], [225, 207, 243], [51, 27, 121], [159, 107, 229], [234, 143, 48], [100, 35, 152], [45, 176, 223], [183, 116, 25], [13, 194, 166], [123, 71, 97], [239, 221, 136], [78, 19, 174], [155, 46, 201], [28, 152, 61], [173, 227, 243], [65, 11, 132], [216, 165, 82], [42, 184, 219], [170, 78, 24], [20, 127, 108], [138, 59, 179], [224, 209, 245], [50, 29, 124], [161, 109, 232], [233, 145, 51], [99, 37, 155], [44, 174, 226], [184, 118, 20], [12, 195, 169], [125, 73, 100], [238, 223, 139], [77, 22, 177], [154, 49, 204], [27, 154, 64], [51, 86, 205] ] 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=(800, 600)), outputs=['plot'], examples=["testimage1.jpg", "testimage2.jpg", "testimage3.jpg"], allow_flagging='never') demo.launch()