diff --git a/NN.npy b/NN.npy new file mode 100644 index 0000000..7e871cb Binary files /dev/null and b/NN.npy differ diff --git a/Xtest.npy b/Xtest.npy new file mode 100644 index 0000000..328bdab Binary files /dev/null and b/Xtest.npy differ diff --git a/Ytest.npy b/Ytest.npy new file mode 100644 index 0000000..604992a Binary files /dev/null and b/Ytest.npy differ diff --git a/numbering.py b/numbering.py new file mode 100644 index 0000000..19ede6d --- /dev/null +++ b/numbering.py @@ -0,0 +1,261 @@ +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) + + +