feat : edit process for load weight

app.py

@@ -18,6 +18,18 @@ tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-base",max_length=60) #xlm
 transformer_model = TFAutoModel.from_pretrained("xlm-roberta-base") #philschmid/tiny-bert-sst2-distilled
 max_seq_length = 32
 
+env_decode ={}
+with open('tf_labels6.json', encoding='utf-8') as fh:
+    env_decode = json.load(fh)
+
+hour_decode={}
+with open('tf_labels7.json', encoding='utf-8') as fh:
+    hour_decode = json.load(fh)
+
+minute_decode={}
+with open('tf_labels8.json', encoding='utf-8') as fh:
+    minute_decode = json.load(fh)
+
 def create_model():
 
   inputs = tf.keras.layers.Input(shape=(max_seq_length,), dtype=tf.int32)
@@ -68,7 +80,18 @@ def create_model():
   output_layer7 = Dense(25, activation='softmax', name='output7')(x7) 
   output_layer8 = Dense(61, activation='softmax', name='output8')(x8) 
 
+  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
   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)
+  model.compile(loss=['binary_crossentropy','binary_crossentropy','binary_crossentropy','binary_crossentropy','binary_crossentropy', 'categorical_crossentropy', 'categorical_crossentropy', 'categorical_crossentropy'], optimizer=opt,
+                metrics=[
+        tf.keras.metrics.BinaryAccuracy(),
+          'categorical_accuracy'
+      ])
+
   model.load_weights("t1_m1.h5")
   return model
 
@@ -127,7 +150,7 @@ def predict(text):
 iface = gr.Interface(
   fn=predict, 
   inputs='text',
-  outputs='text',
+  outputs='label',
   examples=[["Hello! My name is Omar"]]
 )