app.py

app.py

@@ -0,0 +1,97 @@
+import os
+import random
+import numpy as np
+from tqdm import tqdm
+import matplotlib.pyplot as plt
+
+import tensorflow as tf
+import tensorflow_addons as tfa
+from tensorflow import keras
+from tensorflow.keras import layers
+
+from glob import glob
+from PIL import Image
+
+import gradio as gr
+from huggingface_hub import from_pretrained_keras
+
+model = from_pretrained_keras("RobotJelly/GauGAN-Image-generation")
+
+
+
+def predict(image_file):
+  # print(image_file)
+  # img = Image.open(image_file)
+  # image_file = str(img)
+  print("image_file-->", image_file)
+
+  image_list = []
+
+  segmentation_map = image_file.replace("images", "segmentation_map").replace("jpg", "png")
+
+  labels = image_file.replace("images", "segmentation_labels").replace("jpg", "bmp")
+  print("labels", labels)
+
+  image_list = [segmentation_map, image_file, labels]
+
+  image = tf.image.decode_png(tf.io.read_file(image_list[1]), channels=3)
+  image = tf.cast(image, tf.float32) / 127.5 - 1
+
+  segmentation_file = tf.image.decode_png(tf.io.read_file(image_list[0]), channels=3)
+  segmentation_file = tf.cast(segmentation_file, tf.float32)/127.5 - 1
+
+  label_file = tf.image.decode_bmp(tf.io.read_file(image_list[2]), channels=0)
+  label_file = tf.squeeze(label_file)
+
+  image_list = [segmentation_file, image, label_file]
+
+  crop_size = tf.convert_to_tensor((256, 256))
+
+  image_shape = tf.shape(image_list[1])[:2]
+
+  margins = image_shape - crop_size
+
+  y1 = tf.random.uniform(shape=(), maxval=margins[0], dtype=tf.int32)
+  x1 = tf.random.uniform(shape=(), maxval=margins[1], dtype=tf.int32)
+  y2 = y1 + crop_size[0]
+  x2 = x1 + crop_size[1]
+
+  cropped_images = []
+  for img in image_list:
+    cropped_images.append(img[y1:y2, x1:x2])
+
+  final_img_list = [tf.expand_dims(cropped_images[0], axis=0), tf.expand_dims(cropped_images[1], axis=0), tf.expand_dims(tf.one_hot(cropped_images[2], 12), axis=0)]
+
+  # print(final_img_list[0].shape)
+  # print(final_img_list[1].shape)
+  # print(final_img_list[2].shape)
+
+  latent_vector = tf.random.normal(shape=(1, 256), mean=0.0, stddev=2.0)
+
+  # Generate fake images
+  # fake_image = tf.squeeze(model.predict([latent_vector, final_img_list[2]]), axis=0)
+  fake_image = model.predict([latent_vector, final_img_list[2]])
+
+  real_images = final_img_list
+
+  # return tf.squeeze(real_images[1], axis=0), fake_image
+  return [(real_images[0][0]+1)/2, (fake_image[0]+1)/2]
+  
+# input
+input = [gr.inputs.Image(type="filepath", label="Ground Truth - Real Image")]
+
+facades_data = []
+data_dir = 'examples/'
+for idx, images in enumerate(os.listdir(data_dir)):
+  image = os.path.join(data_dir, images)
+  if os.path.isfile(image) and idx < 6:
+    facades_data.append(image)
+
+# output
+output = [gr.outputs.Image(type="numpy", label="Mask/Segmentation used"), gr.outputs.Image(type="numpy", label="Generated - Conditioned Images")]
+
+title = "GauGAN For Conditional Image Generation"
+description = "Upload an Image or take one from examples to generate realistic images that are conditioned on cue images and segmentation maps"
+
+gr.Interface(fn=predict, inputs = input, outputs = output, examples=facades_data, allow_flagging=False, analytics_enabled=False,
+  title=title, description=description, article="<center>Space By: <u><a href='https://github.com/robotjellyzone'><b>Kavya Bisht</b></a></u> \n Based on <a href='https://keras.io/examples/generative/gaugan/'><b>this notebook</b></a></center>").launch(enable_queue=True, debug=True)