Softmax + Categorical Crossentropy

I fixed the activation+loss function, you can't select it directly, it automaticly uses it if it can. I also fixed one-hot generator. Still haven't tested the activation + loss nor any other backward function. I'll do that when I get to the optimizers which is next.

include/neural_network/layer/layer.hpp

@@ -44,6 +44,14 @@ namespace panic{
 
 
 
+enum struct layer_type {
+    unknown,
+    layer_dense,
+    activation_relu,
+    activation_softmax
+};
+
+
 /**
  * @brief Base layer for the rest of the neural network library to use
  *
@@ -85,6 +93,16 @@ struct layer{
 	virtual ~layer() = default;
 
 
+    /**
+     * @brief Virtual layer_type function for derivative layers
+     *
+     * @Note This returns the type of layer it is
+     *    unknown be default
+     */
+     virtual layer_type get_type() const {
+          return layer_type::unknown;
+     }
+
     /**
      * @brief Virtual forward function for derivative layers
      *
@@ -103,7 +121,7 @@ struct layer{
      * @Note It's equal to 0 because it make the derivative 
      * 		object NEEDS to have these function to work.
      */
-	virtual bool backward(const panic::tensor::real_matrix& dinputs) = 0;
+	virtual bool backward(const panic::tensor::real_matrix& dvalues) = 0;
 
 };