revise logic

app.py

@@ -22,17 +22,21 @@ max_seq_length = 32
 env_decode ={}
 with open('tf_labels6.json', encoding='utf-8') as fh:
     env_decode = json.load(fh)
+    env_decode = {int(x):y for x,y in env_decode.items()}
 
 hour_decode={}
 with open('tf_labels7.json', encoding='utf-8') as fh:
     hour_decode = json.load(fh)
+    hour_decode = {int(x):y for x,y in hour_decode.items()}
 
 minute_decode={}
 with open('tf_labels8.json', encoding='utf-8') as fh:
     minute_decode = json.load(fh)
+    minute_decode = {int(x):y for x,y in minute_decode.items()}
 
 def create_model():
 
+  # defined architecture for load_model
   inputs = tf.keras.layers.Input(shape=(max_seq_length,), dtype=tf.int32)
   embedding_layer = transformer_model(inputs)[0]
 
@@ -81,9 +85,10 @@ def create_model():
   output_layer7 = Dense(25, activation='softmax', name='output7')(x7) 
   output_layer8 = Dense(61, activation='softmax', name='output8')(x8) 
 
+  # train only last layer of transformer
   for i,layer in enumerate(transformer_model.roberta.encoder.layer[:-1]):
     transformer_model.roberta.encoder.layer[i].trainable = False
-  # define the model #input_layer inputs
+  # define the model inputs outputs
   model = Model(inputs=inputs , outputs=[output_layer1, output_layer2, output_layer3,output_layer4,output_layer5,output_layer6,output_layer7,output_layer8])
 
   opt = keras.optimizers.Adam(learning_rate=3e-5)
@@ -93,12 +98,20 @@ def create_model():
           'categorical_accuracy'
       ])
 
+  #load weight
   model.load_weights("t1_m1.h5")
   return model
 
 
 model =create_model()
 
+room_dict = {
+    'ห้องนั่งเล่น': 'Living Room','ห้องครัว':'Kitchen','ห้องนอน':'Bedroom','ห้องน้ำ':'Bathroom','ห้องรับประทานอาหาร': 'Dining Room','ห้องสมุด': 'Library','ห้องพักผู้มาเยือน': 'Guest Room','ห้องเล่นเกม':'Game Room','ห้องซักผ้า':'Laundry Room','ระเบียง':'balcony','ไม่มีห้อง':'no room'
+}
+
+scene_dict = {
+    'ซีน เอ':'scene A','ซีน บี':'scene B','ซีน ซี':'scene C','ซีน ดี':'scene D','ซีน อี':'scene E','ซีน เอฟ':'scene F','ซีน จี':'scene G','ซีน เอช':'scene H','ไม่มีซีน':'no scene'
+}
 
 
 def predict(text):
@@ -106,22 +119,22 @@ def predict(text):
   spilt_thai_text = [word_tokenize(x) for x in test_texts]
   new_input_ids = tokenizer(spilt_thai_text, padding=True, truncation=True, return_tensors="tf",is_split_into_words=True)["input_ids"]
   test_padded_sequences = pad_sequences(new_input_ids, maxlen=max_seq_length,padding='post',truncating='post',value=1) #post pre
-  print(test_padded_sequences.shape)
   predicted_labels = model.predict(test_padded_sequences)
-  output = []
+
+  # default answer
+  tmp = {
+        'command' : "not recognized",
+        'room' : None,
+        'device' : None,
+        "hour" : None,
+        "minute": None
+      }
 
   for i in range(len(test_texts)):
-    print(test_texts[i])
     valid = 1 if predicted_labels[0][i] > 0.5 else 0
     is_scene = 1 if predicted_labels[1][i] > 0.5 else 0
     has_num = 1 if predicted_labels[2][i] > 0.5 else 0
-    print(f'is_valid : {valid}')
-    print(f'is_scene : {is_scene}')
-    print(f'has_num : {has_num}')
-
     turn = 1 if predicted_labels[3][i] > 0.5 else 0
-    print(f'turn_on_off : {turn}')
-    print(f'device : ไฟ')
 
     env_id = np.argmax(predicted_labels[5][i])
     env_label = env_decode[env_id]
@@ -131,28 +144,29 @@ def predict(text):
 
     minute_id = np.argmax(predicted_labels[7][i])
     minute_label = minute_decode[minute_id]
-    print(f'env : {env_label}')
-    print(f'hour : {hour_label}')
-    print(f'minute : {minute_label}')
-    print('----')
-    tmp = {
-      'valid' : valid,
-      'is_scene' : is_scene,
-      'has_num' : has_num,
-      'turn_on_off' : turn,
-      'device' : 'ไฟ',
-      'env' : env_label,
-      'hour' : hour,
-      'minute' : minute,
-    }
-  output.append(tmp)
-  return output
+    
+
+    if valid:
+      tmp['device'] = 'ไฟ'
+      tmp['command'] = 'turn on' if turn else 'turn off'
+      if not is_scene:
+        tmp['room'] = room_dict[env_label] if env_label in room_dict  else room_dict['ไม่มีห้อง']
+      else:
+        tmp['room'] = scene_dict[env_label] if env_label in scene_dict  else room_dict['ไม่มีซีน']
+
+      if has_num:
+        tmp['hour'] = hour_label
+        tmp['minute'] = minute_label
+
+
+  return tmp
 
 iface = gr.Interface(
   fn=predict, 
   inputs='text',
-  outputs='label',
-  examples=[["Hello! My name is Omar"]]
+  outputs='json',
+  examples=[["เปิดไฟห้องนอนหน่อย"],["เปิดไฟซีนเอ"],["ปิดไฟห้องรับประทานอาหารเวลา4ทุ่มสามสิบเจ็ดนาที"],['ปิดไฟห้องน้ำเวลาบ่าย���มงห้าสิบนาที'],["โย่ และนี่คือเสียงจากเด็กวัด"]],
+  interpretation="default",
 )
 
 iface.launch()