Add activation choice

chatbot_constructor.py

@@ -30,7 +30,7 @@ def todset(text: str):
 def hash_str(data: str):
     return hashlib.md5(data.encode('utf-8')).hexdigest()
 
-def train(message: str = "", regularization: float = 0.0001, dropout: float = 0.1, learning_rate: float = 0.001, epochs: int = 16, emb_size: int = 128, input_len: int = 16, kernels_count: int = 8, kernel_size: int = 8, left_padding: bool = True, data: str = ""):
+def train(message: str = "", regularization: float = 0.0001, dropout: float = 0.1, learning_rate: float = 0.001, epochs: int = 16, emb_size: int = 128, input_len: int = 16, kernels_count: int = 8, kernel_size: int = 8, left_padding: bool = True, end_activation: str = "softmax", data: str = ""):
     data_hash = None
     if "→" not in data or "\n" not in data:
             if data in os.listdir("cache"):
@@ -77,7 +77,7 @@ def train(message: str = "", regularization: float = 0.0001, dropout: float = 0.
         dropout5_layer = Dropout(dropout)(dense3_layer)
         dense4_layer = Dense(100, activation="tanh", kernel_regularizer=L1(regularization))(dropout5_layer)
         concat2_layer = Concatenate()([dense4_layer, prelu1_layer, attn_flatten_layer, conv1_flatten_layer])
-        dense4_layer = Dense(resps_len, activation="softmax", kernel_regularizer=L1(regularization))(concat2_layer)
+        dense4_layer = Dense(resps_len, activation=end_activation, kernel_regularizer=L1(regularization))(concat2_layer)
         model = Model(inputs=input_layer, outputs=dense4_layer)
         
         X = []
@@ -117,6 +117,7 @@ if __name__ == "__main__":
                                            gr.inputs.Slider(1, 128, default=64, step=1, label="Convolution kernel count"),
                                            gr.inputs.Slider(1, 16, default=8, step=1, label="Convolution kernel size"),
                                            gr.inputs.Checkbox(False, label="Use left padding"),
+                                           gr.inputs.Radio(['softmax', 'sigmoid', 'linear', 'softplus', 'exponential', 'log_softmax'], label="Use left padding"),
                                            "text"],
                          outputs="text")
     iface.launch()