comleted gradient descent

model.py

@@ -53,20 +53,24 @@ def regularization(cost, w1, w2, lamb, m):
     return cost+reg
 
 def gradient(del1, del2, w1, w2, lamb, m):
-    del1,del2 = del1/m, del2/m
+    del1,del2 = del1/m, del2/m    
     tgrad1 = del1[:,1:] + lamb*w1[:,1:]/m
     tgrad2 = del2[:,1:] + lamb*w2[:,1:]/m
-    return np.append(tgrad1.reshape(tgrad1.size), tgrad2.reshape(tgrad2.size))
+
+    w1[:,1:] = np.copy(tgrad1)
+    w2[:,1:] = np.copy(tgrad2)
+
+    return np.append(w1.reshape(w1.size), w2.reshape(w2.size))
 
 def cost(li, lh, lo, weights, X, y, lamb):
-    w1t = weights[:(li+1)*lh]    #28x58
-    w2t = weights[(li+1)*lh:]    #1x29
+    w1 = weights[:(li+1)*lh]    #28x58
+    w2 = weights[(li+1)*lh:]    #1x29
     #28x58, 1x29
     tdel1,tdel2 = np.zeros((lh,li+1),dtype=float), np.zeros((lo,lh+1),dtype=float)
 
     #w1,w2 = getMatrix(lh, li+1, w1t), getMatrix(lo, lh+1, w2t)
-    w1 = np.array(w1t)
-    w2 = np.array(w2t)
+    # w1 = np.array(w1t)
+    # w2 = np.array(w2t)
     #cost
     m = len(X)
     J = 0.0
@@ -100,6 +104,16 @@ def cost(li, lh, lo, weights, X, y, lamb):
 
     return J,grad
 
+def fit(X, y, li, lh, lo, weights, lamb, eta, passes=10000, verbose=True):
+    for i in range(1,passes+1):
+        J, dw = cost(li, lh, lo, weights, X, y, lamb)
+        #print(weights.shape, dw.shape)
+        weights += -eta*dw
+        print(i,"\r", end='')
+        if verbose and i%1000 == 0:
+            print()
+            print(J)
+
 def predict(x, w1, w2):
     x=[1]+x    #58x1
     x = np.array(x)
@@ -115,7 +129,9 @@ if __name__ == "__main__":
     # print(len(X), len(X[0]), len(y), X[0])
     # print(len(tX), len(ty), tX[0])
     li,lh,lo = tuple(params["layers"])
-    weights = [random() for _ in range(lh*(li+1)+lo*(lh+1))]
-    J,grad = cost(li, lh, lo, weights, X, y, 0.1)
-    print(J,grad)
+    weights = np.array([random() for _ in range(lh*(li+1)+lo*(lh+1))])
+    lamb,eta = 0.1,0.1
+    fit(X, y, li, lh, lo, weights, lamb, eta)
+    # J,grad = cost(li, lh, lo, weights, X, y, 0.1)
+    # print(J,grad)
     #print(len(w1), len(w1[0]), len(w2), len(w2[0]))
\ No newline at end of file