From 7e9a93354893088f8529da8b9bd32742daf97bc8 Mon Sep 17 00:00:00 2001
From: eynard <hugo.eynard@gmail.com>
Date: Tue, 14 Dec 2021 22:26:11 +0100
Subject: [PATCH] Un bout de l'entrainement (erreur + partial derivative 1)

---
 sobek/network.py | 37 ++++++++++++++++++++++++++++++-------
 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/sobek/network.py b/sobek/network.py
index 2318dc1..be407af 100755
--- a/sobek/network.py
+++ b/sobek/network.py
@@ -23,7 +23,7 @@ class network:
 
     def __sigmoid(value, derivative=False):
         if (derivative):
-            return __sigmoid(value) * (1 - __sigmoid(value))
+            return network.__sigmoid(value) * (1 - network.__sigmoid(value))
         return 1/(1+np.exp(-value))
 
     def process(self, input, storeValues=False):
@@ -33,24 +33,47 @@ class network:
             raise ValueError("The input vector has the wrong size!")
         if input.dtype != np.float64:
             raise TypeError("The input vector must contain floats!")
+
+        if (storeValues):
+            self.activations = []
+            self.outputs = []
         
         for layerWeights, bias in zip(self.__weights, self.__biases):
             input = np.matmul(input, layerWeights)
             input = np.add(input, bias)
+
+            if (storeValues):
+                self.activations.append(input)
+
             #reLu application
             with np.nditer(input, op_flags=['readwrite']) as layer:
                 for neuron in layer:
                     neuron = network.__reLu(neuron)
+
+            #On peut comparer la performance si on recalcul plus tard
+            if (storeValues):
+                self.outputs.append(input)
         
         return input
 
-    def train(self, inputs, results):
-        self.__outputs = 1
-        #for j in range(1,):
+    def train(self, inputs, desiredOutputs):
+        for input, desiredOutput in zip(inputs, desiredOutputs):
+            self.__output = self.process(input, True)
+            self.__desiredOutput = desiredOutput
         #partialDerivatives
 
-    def __Error(layer, output, desiredOutput):
-        return __ErrorFinalLayerFromValue() if (layer == 1)
+    def __Error(self, layer, neuron):
+        return self.__ErrorFinalLayer(neuron) if (layer == 1) else self.__ErrorHiddenLayer(layer, neuron)
         
     def __ErrorFinalLayer(self, neuron):
-        return __reLu(value, true) * (output - desiredOutput)
\ No newline at end of file
+        return network.__reLu(self.activations[len(self.activations)-1][neuron], True) * (self.__output[neuron] - self.__desiredOutput[neuron])
+
+    def __ErrorHiddenLayer(self, layer, neuron):
+        upperLayerLinksSum = 0
+        for upperLayerNeuron in range(len(self.__weights[layer+1]-1)):
+            #A comparer avec un acces direct au erreurs precalcules
+            upperLayerLinksSum += self.__weights[layer+1][upperLayerNeuron][neuron] * self.__Error(layer+1, neuron)
+        return network.__reLu(self.activations[layer][neuron], True) * upperLayerLinksSum
+
+    def __partialDerivative(self, layer, neuron):
+        return self.__Error(layer, neuron) * self.outputs[layer][neuron]
\ No newline at end of file