Beginning support for multiple implementations

README.md

@@ -1 +1,6 @@
 # loulou
+
+Dependencies : numpy
+Optional dependencies : matplotlib - to show predicted image
+
+* Version 1.0.0 : Initial version, works with another implementation - need some changes

data/.gitignore

@@ -0,0 +1,4 @@
+# Ignore everything in this directory
+*
+# Except this file
+!.gitignore

scripts/rnn.py

@@ -1,17 +1,15 @@
 import numpy as np
 import mnist as mnist
 
+# Fordward propagation
 def feed_forward(X, weights):
     a = [X]
     for w in weights:
-        a.append(np.maximum(a[-1].dot(w),0)) # Calculer l'avancée
-        # np.maximum(val, 0) -> relu
-        # a[-1].dot(w) -> valeur * poids
-        # a.append -> rajouter la valeur à la fin du tableau
+        a.append(np.maximum(a[-1].dot(w),0))
     return a
 
 def grads(X, Y, weights, square):
-    grads = np.empty_like(weights) # grads représente la matrice de correction des poids
+    grads = np.empty_like(weights) # |grads| : weights corrections matrix
     a = feed_forward(X, weights) # on nourrit le réseau et on stocke les valeurs des neurones dans 'a'
     if square:
         delta = a[-1]*a[-1] - Y*Y # on met l'erreur au carré

scripts/run.py

@@ -3,41 +3,48 @@
 import matplotlib.image as image
 import json
 
-#   Erreur si le nombre d'arguments n'est pas bon.
+#   Prediction function (fordward propagation)
+def predire(X, weights):
+    a = [X]
+    for w in weights:
+        a.append(np.maximum(a[-1].dot(w),0))
+    return a
+
+#   Json conversion function
+def saveJson(pred):
+    out = {}
+    out['hot_prediction'] = list(pred)
+    out['prediction'] = int(np.argmax(pred))
+    return json.dumps(out)
+
+#   Handling errors for arguments
 try:
     assert len(sys.argv) == 3
 except AssertionError:
-    print("Erreur ! Veuillez donnez deux arguments, le nom du fichier de poids et de l'image à prédire.")
+    print("Error ! Please give two arguments : path to weights file and to image to predict.")
     exit()
 
-#   On charge les poids
+#   Loading weights matrix
 filename = sys.argv[1]
 try:
     weights = np.load(filename)
 except FileNotFoundError:
-    print("Erreur ! Le fichier de poids n'a pas pu être ouvert, vérifiez qu'il existe bien.")
+    print("Error ! Weights matrix file could not be opened, please check that it exists.")
     print("Fichier : ",filename)
     exit()
 
-#   On charge l'image
+#   Loading image data
 img = sys.argv[2]
 try:
     img = image.imread(img)
 except FileNotFoundError:
-    print("Erreur ! L'image n'a pas pu être ouverte, vérifiez qu'elle existe bien.")
+    print("Error ! Image could not be opened, please check that it exists.")
     print("Image : ",img)
     exit()
 
-def predire(X, weights):
-    a = [X]
-    for w in weights:
-        a.append(np.maximum(a[-1].dot(w),0))
-    return a
-
-out = {}
+#   Shaping image onto matrix
 topred = 1 - img.reshape(784,4).mean(axis=1)
+#   Making prediction
 prediction = predire(topred, weights)[-1]
-out['accuracy'] = list(prediction)
-out['prediction'] = int(np.argmax(prediction))
-out_json = json.dumps(out)
-print(out_json)
+#   Printing json output
+print(saveJson(prediction))

todo.md

@@ -0,0 +1,3 @@
+# To-do - loulou
+
+- [ ] Updating code to use with that implementation

trains/.gitignore

@@ -0,0 +1,6 @@
+# Ignore everything in this directory
+*.*
+# Except those files
+!.gitignore
+!pre-trained/
+!pre-trained/*