262 lines
6.9 KiB
Python
262 lines
6.9 KiB
Python
from sklearn.datasets import load_digits
|
|
import pylab as pl
|
|
import matplotlib.pyplot as plt
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.preprocessing import StandardScaler
|
|
import numpy as np
|
|
import os.path
|
|
import csv
|
|
import random
|
|
|
|
layers_dims=[64,60,10,10]
|
|
|
|
|
|
|
|
|
|
def predict_L_layer(X,parameters):
|
|
AL,caches=L_model_forward(X,parameters)
|
|
|
|
prediction=np.argmax(AL,axis=0)
|
|
|
|
return prediction.reshape(1,prediction.shape[0])
|
|
|
|
|
|
def initialize_parameters_deep(layer_dims):
|
|
np.random.seed(3)
|
|
parameters = {}
|
|
L = len(layer_dims)
|
|
for l in range(1, L):
|
|
parameters['W' + str(l)] = np.random.randn(layer_dims[l],layer_dims[l-1])*0.01
|
|
parameters['b' + str(l)] = np.zeros((layer_dims[l],1))
|
|
|
|
return parameters
|
|
|
|
|
|
def linear_forward(A, W, b):
|
|
Z = np.dot(W,A)+b
|
|
|
|
cache = (A, W, b)
|
|
|
|
return Z, cache
|
|
|
|
def sigmoid_(Z):
|
|
return 1/(1+np.exp(-Z))
|
|
|
|
def relu_(Z):
|
|
return Z*(Z>0)
|
|
|
|
def drelu_(Z):
|
|
return 1. *(Z>0)
|
|
|
|
def dsigmoid_(Z):
|
|
return sigmoid_(Z)*(1-sigmoid_(Z))
|
|
|
|
def sigmoid(Z):
|
|
return sigmoid_(Z),Z
|
|
|
|
def relu(Z):
|
|
return relu_(Z),Z
|
|
|
|
def linear_activation_forward(A_prev,W,b,activation):
|
|
if activation == "sigmoid":
|
|
Z, linear_cache = linear_forward(A_prev,W,b)
|
|
A, activation_cache = sigmoid(Z)
|
|
|
|
elif activation == "relu":
|
|
Z, linear_cache = linear_forward(A_prev,W,b)
|
|
A, activation_cache = relu(Z)
|
|
|
|
cache = (linear_cache, activation_cache)
|
|
|
|
return A, cache
|
|
|
|
def L_model_forward(X, parameters):
|
|
caches = []
|
|
A = X
|
|
L = len(parameters) // 2
|
|
for l in range(1, L):
|
|
A_prev = A
|
|
A, cache = linear_activation_forward(A_prev,parameters['W'+str(l)],parameters['b'+str(l)],"relu")
|
|
caches.append(cache)
|
|
AL, cache = linear_activation_forward(A,parameters['W'+str(L)],parameters['b'+str(L)],"sigmoid")
|
|
caches.append(cache)
|
|
|
|
return AL, caches
|
|
|
|
def compute_cost(AL, Y):
|
|
m=Y.shape[1]
|
|
cost = -(1/m)*np.sum((Y*np.log(AL)+(1-Y)*np.log(1-AL)))
|
|
cost=np.squeeze(cost)
|
|
assert(cost.shape == ())
|
|
return cost
|
|
|
|
def linear_backward(dZ, cache):
|
|
A_prev, W, b = cache
|
|
m = A_prev.shape[1]
|
|
dW = (1/m)*np.dot(dZ,A_prev.T)
|
|
db = (1/m)*np.sum(dZ,axis=1,keepdims=True)
|
|
dA_prev = np.dot(W.T,dZ)
|
|
|
|
return dA_prev, dW, db
|
|
|
|
def relu_backward(dA,activation_cache):
|
|
return dA* drelu_(activation_cache)
|
|
|
|
def sigmoid_backward(dA,activation_cache):
|
|
return dA* dsigmoid_(activation_cache)
|
|
|
|
def linear_activation_backward(dA, cache, activation):
|
|
linear_cache, activation_cache = cache
|
|
if activation == "relu":
|
|
dZ = relu_backward(dA,activation_cache)
|
|
dA_prev, dW, db = linear_backward(dZ,linear_cache)
|
|
|
|
elif activation == "sigmoid":
|
|
dZ = sigmoid_backward(dA,activation_cache)
|
|
dA_prev, dW, db = linear_backward(dZ,linear_cache)
|
|
return dA_prev,dW,db
|
|
|
|
def L_model_backward(AL, Y, caches):
|
|
grads = {}
|
|
L = len(caches)
|
|
m = AL.shape[1]
|
|
#Y = Y.reshape(AL.shape)
|
|
|
|
dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))
|
|
|
|
current_cache = caches[L-1]
|
|
grads["dA" + str(L-1)], grads["dW" + str(L)], grads["db" + str(L)] = linear_activation_backward(dAL,current_cache,"sigmoid")
|
|
|
|
for l in reversed(range(L-1)):
|
|
current_cache = caches[l]
|
|
dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads["dA"+str(l+1)],current_cache,"relu")
|
|
grads["dA" + str(l)] = dA_prev_temp
|
|
grads["dW" + str(l + 1)] = dW_temp
|
|
grads["db" + str(l + 1)] = db_temp
|
|
return grads
|
|
|
|
def update_parameters(parameters, grads, learning_rate):
|
|
L = len(parameters) // 2
|
|
for l in range(L):
|
|
parameters["W" + str(l+1)] = parameters["W" + str(l+1)]-(learning_rate)*grads["dW"+str(l+1)]
|
|
parameters["b" + str(l+1)] = parameters["b" + str(l+1)]-(learning_rate)*grads["db"+str(l+1)]
|
|
return parameters
|
|
|
|
|
|
|
|
def L_layer_model(X, Y, layers_dims, learning_rate = 0.005, num_iterations = 3000, print_cost=False):
|
|
np.random.seed(1)
|
|
costs = []
|
|
|
|
parameters = initialize_parameters_deep(layers_dims)
|
|
|
|
for i in range(0, num_iterations):
|
|
AL, caches = L_model_forward(X, parameters)
|
|
cost = compute_cost(AL, Y)
|
|
grads = L_model_backward(AL, Y, caches)
|
|
parameters = update_parameters(parameters, grads, learning_rate)
|
|
if print_cost and i % 1000 == 0:
|
|
print ("Cost after iteration %i: %f" %(i, cost))
|
|
if print_cost and i % 1000 == 0:
|
|
costs.append(cost)
|
|
# plot the cost
|
|
plt.plot(np.squeeze(costs))
|
|
plt.ylabel('cost')
|
|
plt.xlabel('iterations (per tens)')
|
|
plt.title("Learning rate =" + str(learning_rate))
|
|
plt.show()
|
|
|
|
return parameters
|
|
|
|
|
|
def num(size,target):
|
|
numbers=[]
|
|
imagesx=[]
|
|
imagesy=[]
|
|
|
|
while(len(numbers)!=size):
|
|
x=random.randint(0,np.shape(target)[0]-1)
|
|
y=random.randint(0,np.shape(target)[0]-1)
|
|
|
|
num=str(target[x][1])+str(target[y][1])
|
|
|
|
if(num not in numbers):
|
|
numbers.append(num)
|
|
imagesx.append(target[x][0])
|
|
imagesy.append(target[y][0])
|
|
return(numbers,imagesx,imagesy)
|
|
|
|
def pred(xnum,ynum):
|
|
|
|
xnum=np.array(xnum)
|
|
ynum=np.array(ynum)
|
|
#pl.gray()
|
|
#pl.matshow(xnum[0])
|
|
#pl.show()
|
|
|
|
imgx=xnum.reshape((64,1)).T
|
|
imgx = sc.transform(imgx)
|
|
imgx=imgx.T
|
|
|
|
imgy=ynum.reshape((64,1)).T
|
|
imgy = sc.transform(imgy)
|
|
imgy=imgy.T
|
|
|
|
predicted_digitx=predict_L_layer(imgx,parameters)
|
|
predicted_digity=predict_L_layer(imgy,parameters)
|
|
return int(str(predicted_digitx[0][0]) + str(predicted_digity[0][0]))
|
|
|
|
|
|
|
|
digits=load_digits()
|
|
images_and_labels=list(zip(digits.images,digits.target))
|
|
print()
|
|
|
|
|
|
|
|
n_samples=len(digits.images)
|
|
|
|
|
|
x=digits.images.reshape((n_samples,-1))
|
|
|
|
y=digits.target
|
|
|
|
|
|
|
|
|
|
|
|
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 0)
|
|
np.save('Ytest.npy',y_test )
|
|
np.save('Xtest.npy',X_test )
|
|
|
|
sc = StandardScaler()
|
|
X_train = sc.fit_transform(X_train)
|
|
X_test = sc.transform(X_test)
|
|
|
|
X_train=X_train.T
|
|
X_test=X_test.T
|
|
y_train=y_train.reshape(y_train.shape[0],1)
|
|
y_test=y_test.reshape(y_test.shape[0],1)
|
|
y_train=y_train.T
|
|
y_test=y_test.T
|
|
|
|
|
|
|
|
Y_train_=np.zeros((10,y_train.shape[1]))
|
|
for i in range(y_train.shape[1]):
|
|
Y_train_[y_train[0,i],i]=1
|
|
Y_test_=np.zeros((10,y_test.shape[1]))
|
|
for i in range(y_test.shape[1]):
|
|
Y_test_[y_test[0,i],i]=1
|
|
|
|
|
|
if (os.path.isfile("NN.npy")):
|
|
|
|
parameters=np.load('NN.npy',allow_pickle='TRUE').item()
|
|
else:
|
|
parameters = L_layer_model(X_train, Y_train_, layers_dims, num_iterations = 50000, print_cost = True)
|
|
np.save('NN.npy', parameters)
|
|
|
|
|
|
|