Upload 4 files

app.txt

@@ -0,0 +1,110 @@
+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-cityscapes-1024-1024"
+)
+model = TFSegformerForSemanticSegmentation.from_pretrained(
+    "nvidia/segformer-b0-finetuned-cityscapes-1024-1024"
+)
+
+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 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=["citiscpae-1.jpg", "citiscape-2.jpg"],
+                    allow_flagging='never')
+
+
+demo.launch()

config (1).txt

@@ -0,0 +1,110 @@
+{
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 256,
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "id2label": {
+    "0": "road",
+    "1": "sidewalk",
+    "2": "building",
+    "3": "wall",
+    "4": "fence",
+    "5": "pole",
+    "6": "traffic light",
+    "7": "traffic sign",
+    "8": "vegetation",
+    "9": "terrain",
+    "10": "sky",
+    "11": "person",
+    "12": "rider",
+    "13": "car",
+    "14": "truck",
+    "15": "bus",
+    "16": "train",
+    "17": "motorcycle",
+    "18": "bicycle"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "bicycle": 18,
+    "building": 2,
+    "bus": 15,
+    "car": 13,
+    "fence": 4,
+    "motorcycle": 17,
+    "person": 11,
+    "pole": 5,
+    "rider": 12,
+    "road": 0,
+    "sidewalk": 1,
+    "sky": 10,
+    "terrain": 9,
+    "traffic light": 6,
+    "traffic sign": 7,
+    "train": 16,
+    "truck": 14,
+    "vegetation": 8,
+    "wall": 3
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "reshape_last_stage": true,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0.dev0"
+}

labels (2).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 (2).txt

@@ -0,0 +1,6 @@
+torch
+transformers
+tensorflow
+numpy
+Image
+matplotlib