99 lines
3.0 KiB
Python
99 lines
3.0 KiB
Python
|
from layer import *
|
||
|
|
import numpy as np
|
||
|
|
import pickle
|
||
|
|
import os
|
||
|
|
|
||
|
|
class CheckPoint:
|
||
|
|
def __init__(self,param,accuracy,loss,iteration):
|
||
|
|
super().__init__()
|
||
|
|
self.param = param
|
||
|
|
self.accuracy = accuracy
|
||
|
|
self.loss = loss
|
||
|
|
self.iteration = iteration
|
||
|
|
|
||
|
|
class Model:
|
||
|
|
def __init__(self, layerDim:[int]):
|
||
|
|
super().__init__()
|
||
|
|
gen:np.random.Generator = np.random.default_rng()
|
||
|
|
self.layerDim = layerDim
|
||
|
|
self.param = []
|
||
|
|
self.checkpoints = []
|
||
|
|
self.iteration = 0
|
||
|
|
#...
|
||
|
|
front = 784
|
||
|
|
for sd in layerDim:
|
||
|
|
back = sd
|
||
|
|
weight = Variable(gen.normal(0,1,size=(front,back)))
|
||
|
|
bias = Variable(gen.normal(0,1,size=(back)))
|
||
|
|
self.param.append((weight,bias))
|
||
|
|
front = back
|
||
|
|
|
||
|
|
def caculate(self,input_x,y):
|
||
|
|
input_var = Variable(input_x)
|
||
|
|
Z = input_var
|
||
|
|
for i,(w,b) in enumerate(self.param):
|
||
|
|
U = Z @ w + b
|
||
|
|
if i < len(self.param) - 1:
|
||
|
|
Z = relu(U)
|
||
|
|
else:
|
||
|
|
Z = U
|
||
|
|
J = SoftmaxWithNegativeLogLikelihood(Z,y)
|
||
|
|
return J
|
||
|
|
def train_one_iterate(self,input_x,y,eta):
|
||
|
|
#forward pass
|
||
|
|
J = self.caculate(input_x,y)
|
||
|
|
#backpropagation
|
||
|
|
J.backprop(np.ones(()))
|
||
|
|
for i,(w,b) in enumerate(self.param):
|
||
|
|
w = Variable(w.numpy() - (w.grad) * eta)
|
||
|
|
b = Variable(b.numpy() - (b.grad) * eta)
|
||
|
|
self.param[i] = (w,b)
|
||
|
|
self.iteration += 1
|
||
|
|
return J
|
||
|
|
|
||
|
|
def get_loss_and_confusion(self,input_x,y):
|
||
|
|
J = self.caculate(input_x,y)
|
||
|
|
s = J.softmax_numpy()
|
||
|
|
s = np.round(s)
|
||
|
|
confusion = (np.transpose(y)@s)
|
||
|
|
return J.numpy(), confusion
|
||
|
|
|
||
|
|
def set_checkpoint(self,dev_x,dev_y):
|
||
|
|
J = self.caculate(dev_x,dev_y)
|
||
|
|
loss = np.average(J.numpy())
|
||
|
|
print(f"check point #{len(self.checkpoints)}")
|
||
|
|
print(self.iteration,'iteration : avg loss : ',loss)
|
||
|
|
|
||
|
|
confusion = get_confusion(J)
|
||
|
|
accuracy = get_accuracy_from_confusion(confusion)
|
||
|
|
print('accuracy : {:.2f}%'.format(accuracy * 100))
|
||
|
|
self.checkpoints.append(CheckPoint(
|
||
|
|
self.param,
|
||
|
|
accuracy*100,
|
||
|
|
loss,
|
||
|
|
self.iteration
|
||
|
|
))
|
||
|
|
|
||
|
|
def get_confusion(J:SoftmaxWithNegativeLogLikelihood):
|
||
|
|
s = J.softmax_numpy()
|
||
|
|
s = np.eye(10)[np.argmax(s,axis=len(s.shape)-1)]
|
||
|
|
confusion = (np.transpose(J.y)@s)
|
||
|
|
return confusion
|
||
|
|
|
||
|
|
def get_accuracy_from_confusion(confusion):
|
||
|
|
return np.trace(confusion).sum() / np.sum(confusion)
|
||
|
|
|
||
|
|
def model_filename(layerDim:[int]):
|
||
|
|
return f"model{layerDim}.pickle"
|
||
|
|
|
||
|
|
def save_model(model:Model):
|
||
|
|
with open(model_filename(model.layerDim),"wb") as model_file:
|
||
|
|
pickle.dump(model,model_file)
|
||
|
|
|
||
|
|
def load_or_create_model(layerDim:list):
|
||
|
|
model_name = model_filename(layerDim)
|
||
|
|
if os.path.exists(model_name):
|
||
|
|
with open(model_name,"rb") as model_file:
|
||
|
|
return pickle.load(model_file)
|
||
|
|
else:
|
||
|
|
return Model(layerDim)
|