add base module class

micrograd/nn.py

@@ -2,7 +2,17 @@ import random
 from .engine import Value
 from typing import List, Union
 
-class Neuron:
+class Module:
+
+    def zero_grad(self):
+        for p in self.parameters():
+            p.grad = 0.0
+
+    def parameters(self):
+        return []
+
+class Neuron(Module):
+
     def __init__(self, n_in: int):
         self.w = [Value(random.uniform(-1, 1)) for _ in range(n_in)]
         self.b = Value(random.uniform(-1, 1))
@@ -16,10 +26,11 @@ class Neuron:
             raise ValueError(f"mismatch dimension: x: {len(x)}, w: {len(self.w)}")
         act = reduce(add, [w_i * x_i for w_i, x_i in zip(self.w, x)]) + self.b
         return act.tanh()
+
     def parameters(self):
         return self.w + [self.b]
 
-class Layer:
+class Layer(Module):
     def __init__(self, n_in: int, n_out: int):
         self.neurons = [Neuron(n_in) for _ in range(n_out)]
 
@@ -35,7 +46,7 @@ class Layer:
         return out
 
 
-class MLP:
+class MLP(Module):
     def __init__(self, n_in: int, n_outs: List[int]):
         sizes = [n_in] + n_outs
         self.layers = []

micrograd/train.py

@@ -19,11 +19,10 @@ def model():
         loss = sum([(y_p - y_t)**2 for y_p, y_t in zip(y_pred, y_true)])
 
         # backward
-        for p in n.parameters():
-            p.grad = 0.0
+        n.zero_grad()
         loss.backward()
 
-        # update
+        # update (sgd)
         for p in n.parameters():
             p.data += -lr * p.grad