Atualização do README com créditos

README.md

@@ -11,3 +11,9 @@ license: ecl-2.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+Desenvolvido por Ramon Mayor Martins (2023)
+mail rmayormartins@gmail.com 
+hp https://rmayormartins.github.io/
+twitter @rmayormartins 
+github https://github.com/rmayormartins

app.py

@@ -4,16 +4,16 @@ import numpy as np
 import gradio as gr
 import cv2
 
-# Tamanho padrão para o redimensionamento das imagens
+
 IMAGE_SIZE = (256, 256)
 
-# Carrega o modelo de transferência de estilo pré-treinado
+
 style_transfer_model = hub.load('https://tfhub.dev/google/magenta/arbitrary-image-stylization-v1-256/2')
 
 def load_image(image):
-    # Redimensiona a imagem para o tamanho padrão
+    
     image = cv2.resize(image, IMAGE_SIZE, interpolation=cv2.INTER_AREA)
-    # Processa a imagem para o modelo
+    
     image = image.astype(np.float32)[np.newaxis, ...] / 255.
     if image.shape[-1] == 4:
         image = image[..., :3]
@@ -27,40 +27,40 @@ def apply_sharpness(image, intensity):
     return np.clip(sharp_image, 0, 255)
 
 def interpolate_images(baseline, target, alpha):
-    # Interpola entre duas imagens com um fator alpha
+    
     return baseline + alpha * (target - baseline)
 
 def style_transfer(content_image, style_image, style_density, content_sharpness):
-    # Processa as imagens
+    #
     content_image = load_image(content_image)
     style_image = load_image(style_image)
 
-    # Aplica nitidez na imagem de conteúdo antes da transferência de estilo
+    
     content_image_sharp = apply_sharpness(content_image[0], intensity=content_sharpness)
     content_image_sharp = content_image_sharp[np.newaxis, ...]
 
-    # Executa a transferência de estilo
+    
     stylized_image = style_transfer_model(tf.constant(content_image_sharp), tf.constant(style_image))[0]
 
-    # Interpola entre a imagem de conteúdo e a imagem estilizada para densidade de estilo
+    
     stylized_image = interpolate_images(
         baseline=content_image[0],
         target=stylized_image.numpy(),
         alpha=style_density
     )
 
-    # Converte a imagem resultante para o formato correto
+    
     stylized_image = np.array(stylized_image * 255, np.uint8)
 
-    # Remove a dimensão do batch
+    
     stylized_image = np.squeeze(stylized_image)
     return stylized_image
 
 iface = gr.Interface(
     fn=style_transfer,
     inputs=[
-        gr.Image(label="Content Image"),  # Imagem de conteúdo
-        gr.Image(label="Style Image"),    # Imagem de estilo
+        gr.Image(label="Content Image"),  
+        gr.Image(label="Style Image"),    
         gr.Slider(minimum=0, maximum=1, value=0.5, label="Adjust Style Density"),
         gr.Slider(minimum=0, maximum=1, value=0.5, label="Content Sharpness")
     ],