Fix output activation is none error

chatbot_constructor.py

@@ -14,14 +14,6 @@ import keras
 
 os.mkdir("cache")
 
-class ValueConstraint(Constraint):
-    def __init__(self, min_value: float = -1, max_value: float = 1):
-        self.min_value = min_value
-        self.max_value = max_value
-
-    def __call__(self, w):
-        return K.clip(w, self.min_value, self.max_value)
-
 def todset(text: str):
     lines = [x.rstrip("\n").lower().split("→") for x in text.split("\n")]
     lines = [(x[0].replace("\\n", "\n"), x[1].replace("\\n", "\n")) for x in lines]
@@ -79,7 +71,7 @@ def train(message: str = "", regularization: float = 0.0001, dropout: float = 0.
         concat1_layer = Concatenate()([flatten_layer, attn_flatten_layer, conv1_flatten_layer, conv2_flatten_layer, conv3_flatten_layer])
         dropout2_layer = Dropout(dropout)(concat1_layer)
         dense1_layer = Dense(1024, activation="linear", kernel_regularizer=L1(regularization))(dropout2_layer)
-        prelu1_layer = PReLU(alpha_constraint=ValueConstraint())(dense1_layer)
+        prelu1_layer = PReLU()(dense1_layer)
         dropout3_layer = Dropout(dropout)(prelu1_layer)
         dense2_layer = Dense(512, activation="relu", kernel_regularizer=L1(regularization))(dropout3_layer)
         dropout4_layer = Dropout(dropout)(dense2_layer)
@@ -87,7 +79,10 @@ def train(message: str = "", regularization: float = 0.0001, dropout: float = 0.
         dropout5_layer = Dropout(dropout)(dense3_layer)
         dense4_layer = Dense(256, activation="relu", 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=end_activation, kernel_regularizer=L1(regularization))(concat2_layer)
+        if end_activation is not None:
+            dense4_layer = Dense(resps_len, activation=end_activation, kernel_regularizer=L1(regularization))(concat2_layer)
+        else:
+            dense4_layer = Dense(resps_len, activation="softmax", kernel_regularizer=L1(regularization))(concat2_layer)
         model = Model(inputs=input_layer, outputs=dense4_layer)
         
         X = []