app.py

import gradio as gr
from PIL import Image
import numpy as np
import tensorflow as tf
from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
import os

feature_extractor = SegformerFeatureExtractor.from_pretrained(
    "nvidia/segformer-b1-finetuned-cityscapes-1024-1024"
)
model = TFSegformerForSemanticSegmentation.from_pretrained(
    "nvidia/segformer-b1-finetuned-cityscapes-1024-1024"
)

def ade_palette():
    """ADE20K palette that maps each class to RGB values."""
    return [
        [204, 87, 92],
        [112, 185, 212],
        [45, 189, 106],
        [234, 123, 67],
        [78, 56, 123],
        [210, 32, 89],
        [90, 180, 56],
        [155, 102, 200],
        [33, 147, 176],
        [255, 183, 76],
        [67, 123, 89],
        [190, 60, 45],
        [134, 112, 200],
        [56, 45, 189],
        [200, 56, 123],
        [87, 92, 204],
        [120, 56, 123],
        [45, 78, 123],
        [156, 200, 56]
    ]

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 sepia(input_text):
    # Check if the input text is a valid file path
    if not os.path.isfile(input_text):
        return "Invalid file path. Please enter a valid image file path."

    # Load the image using the input text (assumed to be a path to an image)
    input_img = Image.open(input_text)

    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]
    )
    seg = tf.math.argmax(logits, axis=-1)[0]

    color_seg = np.zeros(
        (seg.shape[0], seg.shape[1], 3), dtype=np.uint8
    )
    for label, color in enumerate(colormap):
        color_seg[seg.numpy() == label, :] = color

    pred_img = np.array(input_img) * 0.5 + color_seg * 0.5
    pred_img = pred_img.astype(np.uint8)

    # Convert the image array to a Pillow (PIL) image
    pred_img = Image.fromarray(pred_img)

    return pred_img

# Define the Gradio interface
iface = gr.Interface(fn=sepia, inputs="image", outputs="image")

# Launch the Gradio app
iface.launch()