Update app.py

app.py

@@ -18,12 +18,13 @@ def generate_latent_points(digit, latent_dim, n_samples, n_classes=10):
 	labels = tf.keras.utils.to_categorical([digit for _ in range(n_samples)], n_classes)
 	return tf.concat([random_latent_vectors, labels], 1)
 
-def create_digit_samples(digit, n_samples, latent_dim=latent_dim):
-    random_vector_labels = generate_latent_points(digit, latent_dim, n_samples)
-    examples = cgan_generator.predict(random_vector_labels)
+def create_digit_samples(digit, n_samples):
+    latent_dim = 128
+    random_vector_labels = generate_latent_points(int(digit), latent_dim, int(n_samples))
+    examples = model.predict(random_vector_labels)
     examples = examples * 255.0
     size = ceil(sqrt(n_samples))
-    digit_images = np.zeros((28*size, 28*size))
+    digit_images = np.zeros((28*size, 28*size), dtype=float)
     n = 0
     for i in range(size):
         for j in range(size):
@@ -31,7 +32,7 @@ def create_digit_samples(digit, n_samples, latent_dim=latent_dim):
                 break
             digit_images[i* 28 : (i+1)*28, j*28 : (j+1)*28] = examples[n, :, :, 0]
             n += 1
-
+    digit_images = (digit_images/127.5) -1
     return digit_images
 
 description = "This model is based on the example created here: https://keras.io/examples/generative/conditional_gan/"