app.py

app.py

@@ -8,16 +8,10 @@ import gradio as gr
 from huggingface_hub import from_pretrained_keras
 
 model = from_pretrained_keras("RobotJelly/GauGAN-Image-generation")
-
-def predict(image_file, segmentation_png, bitmap_img):
-  image_list = [segmentation_png, image_file, bitmap_img]
   
-  #segmentation_map = image_file.replace("images", "segmentation_map").replace("jpg", "png")
-
-  #labels = image_file.replace("images", "segmentation_labels").replace("jpg", "bmp")
-  #print("labels", labels)
+def predict(image_file, segmentation_png, bitmap_img):
 
-  #image_list = [segmentation_map, image_file, labels]
+  image_list = [segmentation_png, image_file, bitmap_img]
 
   image = tf.image.decode_png(tf.io.read_file(image_list[1]), channels=3)
   image = tf.cast(image, tf.float32) / 127.5 - 1
@@ -26,6 +20,8 @@ def predict(image_file, segmentation_png, bitmap_img):
   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.image.rgb_to_grayscale(tf.image.decode_bmp(tf.io.read_file(image_list[2]), channels=3))
+  #print("after decode_bmp --> ", label_file.shape, type(label_file))
   label_file = tf.squeeze(label_file)
 
   image_list = [segmentation_file, image, label_file]
@@ -54,18 +50,15 @@ def predict(image_file, segmentation_png, bitmap_img):
   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]])
+  fake_img = tf.squeeze(fake_image, axis=0)
 
-  #real_images = final_img_list
-  fake = Image.fromarray((fake_image[0]+1)/2)
-  # return tf.squeeze(real_images[1], axis=0), fake_image
-  return fake
+  return np.array(fake_img)
   
 # input
 input = [gr.inputs.Image(type="filepath", label="Ground Truth - Real Image (jpg)"), 
          gr.inputs.Image(type="filepath", label="Segementated image (png)"),
-         gr.inputs.Image(type="filepath", label="corresponding bitmap image (bmp)")]
+         gr.inputs.Image(type="filepath", label="corresponding bitmap image (bmp)", image_mode="L)]
 
 examples = [["facades_data/cmp_b0010.jpg", "facades_data/cmp_b0010.png", "facades_data/cmp_b0010.bmp"],
             ["facades_data/cmp_b0020.jpg", "facades_data/cmp_b0020.png", "facades_data/cmp_b0020.bmp"],
@@ -74,7 +67,7 @@ examples = [["facades_data/cmp_b0010.jpg", "facades_data/cmp_b0010.png", "facade
             ["facades_data/cmp_b0050.jpg", "facades_data/cmp_b0050.png", "facades_data/cmp_b0050.bmp"]]
 
 # output
-output = [gr.outputs.Image(type="pil", label="Generated - Conditioned Images")]
+output = [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"