Update app.py

app.py

@@ -19,21 +19,22 @@ def generate_latent_points(digit, latent_dim, n_samples, n_classes=10):
 	return tf.concat([random_latent_vectors, labels], 1)
 
 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), dtype=float)
-    n = 0
-    for i in range(size):
-        for j in range(size):
-            if n == n_samples:
-                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
+    if digit in range(10):
+        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), dtype=float)
+        n = 0
+        for i in range(size):
+            for j in range(size):
+                if n == n_samples:
+                    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 = "Keras implementation for Conditional GAN to generate samples for specific digit of MNIST"
 article = "Author:<a href=\"https://huggingface.co/rajrathi\"> Rajeshwar Rathi</a>; Based on the keras example by <a href=\"https://keras.io/examples/generative/conditional_gan/\">Sayak Paul</a>"