Update app.py

app.py

@@ -1,49 +1,59 @@
+from tensorflow.keras.layers import GRU
 import tensorflow as tf
 from tensorflow import keras
 import gradio as gr
 
-def generate_text(model,temperature, start_string):
-  char2idx={'\t': 0, '\n': 1, ' ': 2, 'ء': 3, 'آ': 4, 'أ': 5, 'ؤ': 6, 'إ': 7, 'ئ': 8, 'ا': 9, 'ب': 10, 'ة': 11, 'ت': 12, 'ث': 13, 'ج': 14, 'ح': 15, 'خ': 16, 'د': 17, 'ذ': 18, 'ر': 19, 'ز': 20, 'س': 21, 'ش': 22, 'ص': 23, 'ض': 24, 'ط': 25, 'ظ': 26, 'ع': 27, 'غ': 28, 'ف': 29, 'ق': 30, 'ك': 31, 'ل': 32, 'م': 33, 'ن': 34, 'ه': 35, 'و': 36, 'ى': 37, 'ي': 38}
-  idx2char=['\t', '\n', ' ', 'ء', 'آ', 'أ', 'ؤ', 'إ', 'ئ', 'ا', 'ب', 'ة', 'ت',
-       'ث', 'ج', 'ح', 'خ', 'د', 'ذ', 'ر', 'ز', 'س', 'ش', 'ص', 'ض', 'ط',
-       'ظ', 'ع', 'غ', 'ف', 'ق', 'ك', 'ل', 'م', 'ن', 'ه', 'و', 'ى', 'ي']
-  # Evaluation step (generating text using the learned model)
+# Define a custom GRU layer that ignores unsupported arguments
+class CustomGRU(GRU):
+    def __init__(self, **kwargs):
+        kwargs.pop('time_major', None)
+        kwargs.pop('implementation', None)
+        super().__init__(**kwargs)
 
-  # Number of characters to generate
-  num_generate = 1000
+# Register the custom layer
+custom_objects = {'CustomGRU': CustomGRU}
 
-  # Converting our start string to numbers (vectorizing)
-  input_eval = [char2idx[s] for s in start_string]
-  input_eval = tf.expand_dims(input_eval, 0)
+# Load the model with the custom objects
+reconstructed_model = keras.models.load_model("poems_generation_GRU (1).h5", custom_objects=custom_objects)
 
-  # Empty string to store our results
-  text_generated = []
+def generate_text(model, temperature, start_string):
+    char2idx={'\t': 0, '\n': 1, ' ': 2, 'ء': 3, 'آ': 4, 'أ': 5, 'ؤ': 6, 'إ': 7, 'ئ': 8, 'ا': 9, 'ب': 10, 'ة': 11, 'ت': 12, 'ث': 13, 'ج': 14, 'ح': 15, 'خ': 16, 'د': 17, 'ذ': 18, 'ر': 19, 'ز': 20, 'س': 21, 'ش': 22, 'ص': 23, 'ض': 24, 'ط': 25, 'ظ': 26, 'ع': 27, 'غ': 28, 'ف': 29, 'ق': 30, 'ك': 31, 'ل': 32, 'م': 33, 'ن': 34, 'ه': 35, 'و': 36, 'ى': 37, 'ي': 38}
+    idx2char=['\t', '\n', ' ', 'ء', 'آ', 'أ', 'ؤ', 'إ', 'ئ', 'ا', 'ب', 'ة', 'ت', 'ث', 'ج', 'ح', 'خ', 'د', 'ذ', 'ر', 'ز', 'س', 'ش', 'ص', 'ض', 'ط', 'ظ', 'ع', 'غ', 'ف', 'ق', 'ك', 'ل', 'م', 'ن', 'ه', 'و', 'ى', 'ي']
+    # Evaluation step (generating text using the learned model)
 
-  # Low temperatures results in more predictable text.
-  # Higher temperatures results in more surprising text.
-  # Experiment to find the best setting.
+    # Number of characters to generate
+    num_generate = 1000
 
-  # Here batch size == 1
-  model.reset_states()
-  for i in range(num_generate):
-      predictions = model(input_eval)
-      # remove the batch dimension
-      predictions = tf.squeeze(predictions, 0)
+    # Converting our start string to numbers (vectorizing)
+    input_eval = [char2idx[s] for s in start_string]
+    input_eval = tf.expand_dims(input_eval, 0)
 
-      # using a random.categorical distribution to predict the word returned by the model
-      predictions = predictions / temperature
-      predicted_id = tf.random.categorical(predictions, num_samples=1)[-1,0].numpy()
-      
-      input_eval = tf.expand_dims([predicted_id], 0)
+    # Empty string to store our results
+    text_generated = []
 
-      text_generated.append(idx2char[predicted_id])
+    # Low temperatures results in more predictable text.
+    # Higher temperatures results in more surprising text.
+    # Experiment to find the best setting.
 
-  return (start_string + ''.join(text_generated))
+    # Here batch size == 1
+    model.reset_states()
+    for i in range(num_generate):
+        predictions = model(input_eval)
+        # remove the batch dimension
+        predictions = tf.squeeze(predictions, 0)
 
-reconstructed_model = keras.models.load_model("poems_generation_GRU (1).h5")
+        # using a random.categorical distribution to predict the word returned by the model
+        predictions = predictions / temperature
+        predicted_id = tf.random.categorical(predictions, num_samples=1)[-1,0].numpy()
+        
+        input_eval = tf.expand_dims([predicted_id], 0)
 
-def generate_poem(start,temperature):
-    return generate_text(reconstructed_model,temperature, start_string=u""+start )
+        text_generated.append(idx2char[predicted_id])
 
-iface = gr.Interface(fn=generate_poem, inputs=["text",gr.Slider(0, 1, value=1)], outputs="text")
+    return (start_string + ''.join(text_generated))
+
+def generate_poem(start, temperature):
+    return generate_text(reconstructed_model, temperature, start_string=u""+start)
+
+iface = gr.Interface(fn=generate_poem, inputs=["text", gr.Slider(0, 1, value=1)], outputs="text")
 iface.launch()