Compare commits
No commits in common. 'master' and 'b39d143adc757fa84926ba305f469eefb95b0f8b' have entirely different histories.
master
...
b39d143adc
Binary file not shown.
@ -1,39 +0,0 @@
|
|||||||
'''
|
|
||||||
Author: SJ2050
|
|
||||||
Date: 2021-11-21 17:22:02
|
|
||||||
LastEditTime: 2021-11-21 22:05:09
|
|
||||||
Version: v0.0.1
|
|
||||||
Description: Use softmax regression method to solve multiclass classification problems.
|
|
||||||
Copyright © 2021 SJ2050
|
|
||||||
'''
|
|
||||||
|
|
||||||
import matplotlib.pyplot as plt
|
|
||||||
from sklearn.datasets import load_digits
|
|
||||||
from sklearn.linear_model import LogisticRegression
|
|
||||||
from sklearn.metrics import confusion_matrix
|
|
||||||
from sklearn.metrics import accuracy_score
|
|
||||||
from softmax_regression import SoftmaxRegression
|
|
||||||
|
|
||||||
# load data
|
|
||||||
digits = load_digits()
|
|
||||||
x_train = digits.data[:-500]
|
|
||||||
y_train = digits.target[:-500]
|
|
||||||
softmax_reg = SoftmaxRegression()
|
|
||||||
softmax_reg.train(x_train, y_train)
|
|
||||||
|
|
||||||
# plot confusion matrix
|
|
||||||
x_test = digits.data[-500:]
|
|
||||||
y_test = digits.target[-500:]
|
|
||||||
pred_train = softmax_reg.predict(x_train)
|
|
||||||
pred_test = softmax_reg.predict(x_test)
|
|
||||||
|
|
||||||
print(f'accuracy train = {accuracy_score(y_train, pred_train)}')
|
|
||||||
print(f'accuracy test = {accuracy_score(y_test, pred_test)}')
|
|
||||||
|
|
||||||
cm = confusion_matrix(y_test, pred_test)
|
|
||||||
plt.matshow(cm)
|
|
||||||
plt.title(u'Confusion Matrix')
|
|
||||||
plt.colorbar()
|
|
||||||
plt.ylabel(u'Groundtruth')
|
|
||||||
plt.xlabel(u'Predict')
|
|
||||||
plt.show()
|
|
||||||
@ -1,38 +0,0 @@
|
|||||||
'''
|
|
||||||
Author: SJ2050
|
|
||||||
Date: 2021-11-21 18:24:41
|
|
||||||
LastEditTime: 2021-11-21 18:50:47
|
|
||||||
Version: v0.0.1
|
|
||||||
Description: Use sklearn to solve logistic regression problems.
|
|
||||||
Copyright © 2021 SJ2050
|
|
||||||
'''
|
|
||||||
import matplotlib.pyplot as plt
|
|
||||||
from sklearn.datasets import load_digits
|
|
||||||
from sklearn.linear_model import LogisticRegression
|
|
||||||
from sklearn.metrics import confusion_matrix
|
|
||||||
from sklearn.metrics import accuracy_score
|
|
||||||
|
|
||||||
# load data
|
|
||||||
digits = load_digits()
|
|
||||||
x_train = digits.data[:-500]
|
|
||||||
y_train = digits.target[:-500]
|
|
||||||
|
|
||||||
log_reg=LogisticRegression()
|
|
||||||
log_reg.fit(x_train, y_train)
|
|
||||||
|
|
||||||
# plot confusion matrix
|
|
||||||
x_test = digits.data[-500:]
|
|
||||||
y_test = digits.target[-500:]
|
|
||||||
pred_train = log_reg.predict(x_train)
|
|
||||||
pred_test = log_reg.predict(x_test)
|
|
||||||
|
|
||||||
print(f'accuracy train = {accuracy_score(y_train, pred_train)}')
|
|
||||||
print(f'accuracy test = {accuracy_score(y_test, pred_test)}')
|
|
||||||
|
|
||||||
cm = confusion_matrix(y_test, pred_test)
|
|
||||||
plt.matshow(cm)
|
|
||||||
plt.title(u'Confusion Matrix')
|
|
||||||
plt.colorbar()
|
|
||||||
plt.ylabel(u'Groundtruth')
|
|
||||||
plt.xlabel(u'Predict')
|
|
||||||
plt.show()
|
|
||||||
@ -1,101 +0,0 @@
|
|||||||
'''
|
|
||||||
Author: SJ2050
|
|
||||||
Date: 2021-11-21 17:06:31
|
|
||||||
LastEditTime: 2021-11-22 10:18:42
|
|
||||||
Version: v0.0.1
|
|
||||||
Description: Softmax regerssion.
|
|
||||||
Copyright © 2021 SJ2050
|
|
||||||
'''
|
|
||||||
import numpy as np
|
|
||||||
|
|
||||||
def softmax(Z):
|
|
||||||
assert(len(Z.shape) == 2 and Z.shape[1] == 1, 'Z should be a column vector!')
|
|
||||||
Z_exp = np.exp(Z)
|
|
||||||
return Z_exp/Z_exp.sum(0, keepdims=True)
|
|
||||||
|
|
||||||
class SoftmaxRegression():
|
|
||||||
def __init__(self):
|
|
||||||
self.is_trained = False
|
|
||||||
pass
|
|
||||||
|
|
||||||
def train(self, train_data, train_label, num_iterations=150, alpha=0.01):
|
|
||||||
self.train_data = train_data
|
|
||||||
self.train_label = train_label
|
|
||||||
self.classes = np.unique(self.train_label)
|
|
||||||
self.out_dim = len(self.classes)
|
|
||||||
|
|
||||||
train_data_num, self.inp_dim = np.shape(self.train_data)
|
|
||||||
self.weights = np.random.random((self.inp_dim, self.out_dim))
|
|
||||||
self.b = np.random.random((self.out_dim, 1))
|
|
||||||
|
|
||||||
for j in range(num_iterations):
|
|
||||||
print(f'iteration: {j}')
|
|
||||||
data_index = list(range(train_data_num))
|
|
||||||
for i in range(train_data_num):
|
|
||||||
rand_index = int(np.random.uniform(0, len(data_index)))
|
|
||||||
x_arr = self.train_data[rand_index]
|
|
||||||
x_vec = x_arr.reshape(-1, 1)
|
|
||||||
x = np.array([x_arr for _ in range(self.out_dim)]).T
|
|
||||||
softmax_values = softmax(np.dot(self.weights.T, x_vec)+self.b).reshape(-1)
|
|
||||||
label =self.train_label[rand_index]
|
|
||||||
cls = np.argwhere(self.classes == label)[0][0]
|
|
||||||
y_arr = np.zeros(self.out_dim)
|
|
||||||
y_arr[cls] = 1
|
|
||||||
err_arr = y_arr-softmax_values
|
|
||||||
err_vec = err_arr.reshape(-1, 1)
|
|
||||||
err = np.diag(err_arr)
|
|
||||||
|
|
||||||
self.weights += alpha*np.dot(x, err)
|
|
||||||
self.b += alpha*err_vec
|
|
||||||
|
|
||||||
self.is_trained = True
|
|
||||||
|
|
||||||
def predict(self, predict_data):
|
|
||||||
if self.is_trained:
|
|
||||||
predict_num = len(predict_data)
|
|
||||||
result = np.empty(predict_num)
|
|
||||||
|
|
||||||
result = [self.classes[np.argmax(softmax(np.dot(self.weights.T, \
|
|
||||||
predict_data[i].reshape(-1, 1))+self.b))] \
|
|
||||||
for i in range(predict_num)]
|
|
||||||
|
|
||||||
return np.array(result)
|
|
||||||
else:
|
|
||||||
print('Need training before predicting!!')
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
|
||||||
# test binary classsfication
|
|
||||||
import matplotlib.pyplot as plt
|
|
||||||
import sklearn.datasets
|
|
||||||
from sklearn.metrics import accuracy_score
|
|
||||||
|
|
||||||
def plot_decision_boundary(predict_func, data, label):
|
|
||||||
"""画出结果图
|
|
||||||
Args:
|
|
||||||
pred_func (callable): 预测函数
|
|
||||||
data (numpy.ndarray): 训练数据集合
|
|
||||||
label (numpy.ndarray): 训练数据标签
|
|
||||||
"""
|
|
||||||
x_min, x_max = data[:, 0].min() - .5, data[:, 0].max() + .5
|
|
||||||
y_min, y_max = data[:, 1].min() - .5, data[:, 1].max() + .5
|
|
||||||
h = 0.01
|
|
||||||
|
|
||||||
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
|
|
||||||
|
|
||||||
Z = predict_func(np.c_[xx.ravel(), yy.ravel()])
|
|
||||||
Z = Z.reshape(xx.shape)
|
|
||||||
|
|
||||||
plt.contourf(xx, yy, Z, cmap=plt.cm.Spectral) #画出登高线并填充
|
|
||||||
plt.scatter(data[:, 0], data[:, 1], c=label, cmap=plt.cm.Spectral)
|
|
||||||
plt.show()
|
|
||||||
|
|
||||||
data, label = sklearn.datasets.make_moons(200, noise=0.30)
|
|
||||||
plt.scatter(data[:,0], data[:,1], c=label)
|
|
||||||
plt.title("Original Data")
|
|
||||||
|
|
||||||
softmax_reg = SoftmaxRegression()
|
|
||||||
softmax_reg.train(data, label, 200)
|
|
||||||
plot_decision_boundary(lambda x: softmax_reg.predict(x), data, label)
|
|
||||||
y_train = softmax_reg.predict(data)
|
|
||||||
print(f'accuracy train = {accuracy_score(label, y_train)}')
|
|
||||||
|
Before Width: | Height: | Size: 21 KiB |
|
Before Width: | Height: | Size: 22 KiB |
|
Before Width: | Height: | Size: 17 KiB |
|
Before Width: | Height: | Size: 17 KiB |
@ -1,191 +0,0 @@
|
|||||||
'''
|
|
||||||
Author: SJ2050
|
|
||||||
Date: 2022-01-21 16:57:04
|
|
||||||
LastEditTime: 2022-01-22 10:58:38
|
|
||||||
Version: v0.0.1
|
|
||||||
Description: Full connection multi-layer perceptron class declaration.
|
|
||||||
Copyright © 2022 SJ2050
|
|
||||||
'''
|
|
||||||
import numpy as np
|
|
||||||
from sklearn.metrics import accuracy_score
|
|
||||||
|
|
||||||
class FullConnectionMLP:
|
|
||||||
# nodes_size: each layers size.
|
|
||||||
# activation_func: activation function of hidden layers
|
|
||||||
# (only support `sigmoid` now).
|
|
||||||
# output_activation_func: activation function of output layer.
|
|
||||||
# If value is `sigmoid`, then error function
|
|
||||||
# will use mean square loss function. If value
|
|
||||||
# is `softmax`, then cross entropy loss function
|
|
||||||
# will be used.
|
|
||||||
def __init__(self, nodes_size,
|
|
||||||
activation_func='sigmoid',
|
|
||||||
output_activation_func='softmax'):
|
|
||||||
self.nodes_size = nodes_size
|
|
||||||
self.activation_func = activation_func
|
|
||||||
self.output_activation_func = output_activation_func
|
|
||||||
|
|
||||||
total_layer_num = len(nodes_size)
|
|
||||||
self.layer_num = total_layer_num
|
|
||||||
self.layers = [np.array([]) for _ in range(total_layer_num)]
|
|
||||||
self.w = []
|
|
||||||
self.b = []
|
|
||||||
# initialize weights and biases
|
|
||||||
for i in range(0, total_layer_num-1):
|
|
||||||
self.w.append(np.random.random((nodes_size[i], nodes_size[i+1]))*2-1)
|
|
||||||
self.b.append(np.zeros(nodes_size[i+1]))
|
|
||||||
|
|
||||||
def __activate_func(self, activation_name):
|
|
||||||
if activation_name == 'sigmoid':
|
|
||||||
y_func = lambda x: 1/(1+np.exp(-x))
|
|
||||||
dy_func = lambda y: y*(1-y)
|
|
||||||
elif activation_name == 'softmax':
|
|
||||||
y_func = lambda x: np.exp(x)/np.sum(np.exp(x), axis=1, keepdims=True)
|
|
||||||
dy_func = lambda yi, yj, equal: yi*(1-yi) if equal else -yi*yj
|
|
||||||
else:
|
|
||||||
raise RuntimeError('Unsupported activation name!!')
|
|
||||||
|
|
||||||
return (y_func, dy_func)
|
|
||||||
|
|
||||||
def forward(self, X_input):
|
|
||||||
# for input layer
|
|
||||||
self.layers[0] = X_input
|
|
||||||
|
|
||||||
# for hidden layers
|
|
||||||
X = X_input
|
|
||||||
(y_func, _) = self.__activate_func(self.activation_func)
|
|
||||||
for i in range(0, self.layer_num - 2):
|
|
||||||
w = self.w[i]
|
|
||||||
b = self.b[i]
|
|
||||||
X = y_func(np.matmul(X, w)+b)
|
|
||||||
self.layers[i+1] = X
|
|
||||||
|
|
||||||
# for output layer
|
|
||||||
(y_func, _) = self.__activate_func(self.output_activation_func)
|
|
||||||
w = self.w[-1]
|
|
||||||
b = self.b[-1]
|
|
||||||
X = y_func(np.matmul(X, w)+b)
|
|
||||||
self.layers[-1] = X
|
|
||||||
|
|
||||||
def backward(self, X_input, label_tags, eps = 0.1):
|
|
||||||
t = label_tags
|
|
||||||
|
|
||||||
self.forward(X_input)
|
|
||||||
D = []
|
|
||||||
# delta of output layer
|
|
||||||
x = self.layers[-2]
|
|
||||||
y = self.layers[-1]
|
|
||||||
if (self.output_activation_func == 'sigmoid'):
|
|
||||||
# use mean square loss function
|
|
||||||
(_, dy_func) = self.__activate_func(self.output_activation_func)
|
|
||||||
d = dy_func(y)*(t-y)
|
|
||||||
elif (self.output_activation_func == 'softmax'):
|
|
||||||
# use cross entropy loss function
|
|
||||||
(_, dy_func) = self.__activate_func(self.output_activation_func)
|
|
||||||
d = (t-y)
|
|
||||||
else:
|
|
||||||
raise RuntimeError('Unsupported output_activation name!!')
|
|
||||||
D.insert(0, d)
|
|
||||||
|
|
||||||
if (self.activation_func == 'sigmoid'):
|
|
||||||
(_, dy_func) = self.__activate_func(self.activation_func)
|
|
||||||
for j in range(self.layer_num-2, 0, -1):
|
|
||||||
i = j - 1
|
|
||||||
y = self.layers[j]
|
|
||||||
w = self.w[j]
|
|
||||||
d = dy_func(y)*np.matmul(d, w.T)
|
|
||||||
D.insert(0, d)
|
|
||||||
else:
|
|
||||||
raise RuntimeError('activation function of hidden layer only support sigmoid now!')
|
|
||||||
|
|
||||||
# update weights and biases
|
|
||||||
for j in range(self.layer_num-1, 0, -1):
|
|
||||||
i = j - 1
|
|
||||||
x = self.layers[i]
|
|
||||||
d = D[i]
|
|
||||||
self.w[i] += eps*np.matmul(x.T, d)/x.shape[0]
|
|
||||||
self.b[i] += eps*np.sum(d, axis=0)/x.shape[0]
|
|
||||||
|
|
||||||
def evaluate(self, label_tags):
|
|
||||||
output_layer = self.layers[-1]
|
|
||||||
loss = np.mean(0.5*np.linalg.norm(output_layer - label_tags, axis=1)**2)
|
|
||||||
|
|
||||||
y_pred = np.argmax(output_layer, axis=1)
|
|
||||||
y_true = np.argmax(label_tags, axis=1)
|
|
||||||
acc = accuracy_score(y_true, y_pred)
|
|
||||||
|
|
||||||
return (loss, acc)
|
|
||||||
|
|
||||||
def train(self, X_input, label_tags, eps=0.1, iter_num=2000, eval_num=100, batch_size=100):
|
|
||||||
print('Training...')
|
|
||||||
for i in range(iter_num):
|
|
||||||
if (batch_size < 0):
|
|
||||||
batch_input = X_input
|
|
||||||
batch_tags = label_tags
|
|
||||||
else:
|
|
||||||
index = np.random.randint(0, X_input.shape[0], batch_size)
|
|
||||||
batch_input = X_input[index]
|
|
||||||
batch_tags = label_tags[index]
|
|
||||||
self.backward(batch_input, batch_tags, eps)
|
|
||||||
|
|
||||||
if (i+1) % eval_num == 0:
|
|
||||||
self.forward(X_input)
|
|
||||||
loss, acc = self.evaluate(label_tags)
|
|
||||||
print(f'{i+1}th training of {iter_num}: Loss={loss}, acc={acc}.')
|
|
||||||
print('Training finished!')
|
|
||||||
return self.layers[-1]
|
|
||||||
|
|
||||||
def predict(self, X_input):
|
|
||||||
self.forward(X_input)
|
|
||||||
return self.layers[-1]
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
|
||||||
from sklearn.datasets import load_digits
|
|
||||||
from sklearn.metrics import confusion_matrix
|
|
||||||
import matplotlib.pyplot as plt
|
|
||||||
|
|
||||||
# load data
|
|
||||||
digits = load_digits()
|
|
||||||
X = digits.data
|
|
||||||
Y = digits.target
|
|
||||||
X -= X.min()
|
|
||||||
X /= X.max()
|
|
||||||
|
|
||||||
x_train = X[:-500]
|
|
||||||
y_train = Y[:-500]
|
|
||||||
y_train_tags = np.zeros((x_train.shape[0], 10))
|
|
||||||
for i in range(10):
|
|
||||||
y_train_tags[np.where(y_train == i), i] = 1
|
|
||||||
|
|
||||||
# initialize NN model
|
|
||||||
nodes_size = [64, 100, 10]
|
|
||||||
fc_mlp = FullConnectionMLP(nodes_size, activation_func='sigmoid',
|
|
||||||
output_activation_func='softmax')
|
|
||||||
pred_train = fc_mlp.train(x_train, y_train_tags, eps=0.1, iter_num=20000,
|
|
||||||
eval_num=100, batch_size=100)
|
|
||||||
(loss, acc) = fc_mlp.evaluate(y_train_tags)
|
|
||||||
print('--------------------------------')
|
|
||||||
print(f'train: Loss={loss}, acc={acc}.')
|
|
||||||
|
|
||||||
x_test = X[-500:]
|
|
||||||
y_test = Y[-500:]
|
|
||||||
y_test_tags = np.zeros((x_test.shape[0], 10))
|
|
||||||
for i in range(10):
|
|
||||||
y_test_tags[np.where(y_test == i), i] = 1
|
|
||||||
|
|
||||||
y_res = fc_mlp.predict(x_test)
|
|
||||||
y_test_pred = np.argmax(y_res, axis=1)
|
|
||||||
# print(f'aa {y_test_pred[0]}; {y_res[0]}')
|
|
||||||
# print(f'bb {y_test_pred[1]}; {y_res[1]}')
|
|
||||||
(loss, acc) = fc_mlp.evaluate(y_test_tags)
|
|
||||||
print('--------------------------------')
|
|
||||||
print(f'predict: Loss={loss}, acc={acc}.')
|
|
||||||
|
|
||||||
cm = confusion_matrix(y_test, y_test_pred)
|
|
||||||
plt.matshow(cm)
|
|
||||||
plt.title(u'Confusion Matrix')
|
|
||||||
plt.colorbar()
|
|
||||||
plt.ylabel(u'Groundtruth')
|
|
||||||
plt.xlabel(u'Predict')
|
|
||||||
plt.show()
|
|
||||||
@ -1,155 +0,0 @@
|
|||||||
'''
|
|
||||||
Author: SJ2050
|
|
||||||
Date: 2022-01-16 17:16:10
|
|
||||||
LastEditTime: 2022-01-22 10:09:33
|
|
||||||
Version: v0.0.1
|
|
||||||
Description: Forward-Propagation and Back-Propagation algorithms of MLP using function.
|
|
||||||
Copyright © 2022 SJ2050
|
|
||||||
'''
|
|
||||||
import numpy as np
|
|
||||||
from sklearn.metrics import accuracy_score
|
|
||||||
|
|
||||||
# NN = {'nodes_size': [ ],
|
|
||||||
# 'layers': [ ],
|
|
||||||
# 'w': [ ],
|
|
||||||
# 'b': [ ]}
|
|
||||||
|
|
||||||
def sigmoid(x):
|
|
||||||
y = 1 / (1+np.exp(-x))
|
|
||||||
return y
|
|
||||||
|
|
||||||
def sigmoid_derivative(y):
|
|
||||||
return y * (1-y)
|
|
||||||
|
|
||||||
def initialize(nodes_size):
|
|
||||||
NN = {}
|
|
||||||
NN['nodes_size'] = nodes_size
|
|
||||||
total_layer_num = len(nodes_size)
|
|
||||||
NN['layers'] = [np.array([]) for _ in range(total_layer_num)]
|
|
||||||
NN['w'] = []
|
|
||||||
NN['b'] = []
|
|
||||||
|
|
||||||
for i in range(0, total_layer_num-1):
|
|
||||||
NN['w'].append(np.random.random((nodes_size[i], nodes_size[i+1]))*2-1)
|
|
||||||
NN['b'].append(np.zeros(nodes_size[i+1]))
|
|
||||||
|
|
||||||
return NN
|
|
||||||
|
|
||||||
def forward_propagation(NN, input_layer):
|
|
||||||
layer_num = len(NN['nodes_size'])
|
|
||||||
NN['layers'][0] = input_layer
|
|
||||||
|
|
||||||
x = input_layer
|
|
||||||
for i in range(0, layer_num-1):
|
|
||||||
w = NN['w'][i]
|
|
||||||
b = NN['b'][i]
|
|
||||||
x = sigmoid(np.matmul(x, w)+b)
|
|
||||||
NN['layers'][i+1] = x
|
|
||||||
|
|
||||||
def backward_propagation(NN, input_layer, tags, eps = 0.01):
|
|
||||||
layer_num = len(NN['nodes_size'])
|
|
||||||
t = tags
|
|
||||||
|
|
||||||
forward_propagation(NN, input_layer)
|
|
||||||
D = []
|
|
||||||
# compute delta
|
|
||||||
for j in range(layer_num-1, 0, -1):
|
|
||||||
i = j - 1
|
|
||||||
x = NN['layers'][i]
|
|
||||||
y = NN['layers'][j]
|
|
||||||
if j == layer_num - 1:
|
|
||||||
d = sigmoid_derivative(y)*(t-y)
|
|
||||||
else:
|
|
||||||
w = NN['w'][j]
|
|
||||||
d = sigmoid_derivative(y)*np.matmul(d, w.T)
|
|
||||||
|
|
||||||
D.insert(0, d)
|
|
||||||
|
|
||||||
# update weights and biases
|
|
||||||
for j in range(layer_num-1, 0, -1):
|
|
||||||
i = j - 1
|
|
||||||
x = NN['layers'][i]
|
|
||||||
d = D[i]
|
|
||||||
NN['w'][i] += eps*np.matmul(x.T, d) / x.shape[0]
|
|
||||||
NN['b'][i] += eps*np.sum(d, axis=0) / x.shape[0]
|
|
||||||
|
|
||||||
def train(NN, input_layer, tags, eps, iter_num, eval_num, batch_size):
|
|
||||||
print('Training...')
|
|
||||||
for i in range(iter_num):
|
|
||||||
# print(f'{i+1}th training of {iter_num}.')
|
|
||||||
if (batch_size < 0):
|
|
||||||
batch_input = input_layer
|
|
||||||
batch_tags = tags
|
|
||||||
else:
|
|
||||||
index = np.random.randint(0, input_layer.shape[0], batch_size)
|
|
||||||
batch_input = input_layer[index]
|
|
||||||
batch_tags = tags[index]
|
|
||||||
backward_propagation(NN, batch_input, batch_tags, eps)
|
|
||||||
|
|
||||||
if (i+1) % eval_num == 0:
|
|
||||||
forward_propagation(NN, input_layer)
|
|
||||||
loss, acc = evaluate(NN, tags)
|
|
||||||
print(f'{i+1}th training of {iter_num}: Loss={loss}, acc={acc}.')
|
|
||||||
print('Training finished!')
|
|
||||||
return NN['layers'][-1]
|
|
||||||
|
|
||||||
def predict(NN, input_layer):
|
|
||||||
forward_propagation(NN, input_layer)
|
|
||||||
return NN['layers'][-1]
|
|
||||||
|
|
||||||
def evaluate(NN, tags):
|
|
||||||
output_layer = NN['layers'][-1]
|
|
||||||
loss = np.mean(0.5*np.linalg.norm(output_layer - tags, axis=1)**2)
|
|
||||||
|
|
||||||
y_pred = np.argmax(output_layer, axis=1)
|
|
||||||
y_true = np.argmax(tags, axis=1)
|
|
||||||
acc = accuracy_score(y_true, y_pred)
|
|
||||||
|
|
||||||
# print(f'Loss = {loss}, acc = {acc}.')
|
|
||||||
return (loss, acc)
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
|
||||||
from sklearn import datasets, linear_model
|
|
||||||
import matplotlib.pyplot as plt
|
|
||||||
# generate sample data
|
|
||||||
np.random.seed(0)
|
|
||||||
X, y_true = datasets.make_moons(400, noise=0.20)
|
|
||||||
tags = np.zeros((X.shape[0], 2))
|
|
||||||
tags[np.where(y_true == 0), 0] = 1
|
|
||||||
tags[np.where(y_true == 1), 1] = 1
|
|
||||||
|
|
||||||
x_train = X[:200]
|
|
||||||
y_train_tags = tags[:200]
|
|
||||||
x_test = X[200:]
|
|
||||||
y_test_tags = tags[200:]
|
|
||||||
# plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Spectral)
|
|
||||||
# plt.show()
|
|
||||||
|
|
||||||
# initialize NN model
|
|
||||||
nodes_size = [2, 8, 2]
|
|
||||||
NN = initialize(nodes_size)
|
|
||||||
# train
|
|
||||||
y_res = train(NN, x_train, y_train_tags,
|
|
||||||
eps=0.1, iter_num=100000,
|
|
||||||
eval_num=1000, batch_size=-1)
|
|
||||||
y_train_pred = np.argmax(y_res, axis=1)
|
|
||||||
(loss, acc) = evaluate(NN, y_train_tags)
|
|
||||||
print('--------------------------------')
|
|
||||||
print(f'train: Loss={loss}, acc={acc}.')
|
|
||||||
|
|
||||||
# predict result
|
|
||||||
y_res = predict(NN, x_test)
|
|
||||||
y_test_pred = np.argmax(y_res, axis=1)
|
|
||||||
|
|
||||||
# plot
|
|
||||||
plt.scatter(x_test[:, 0], x_test[:, 1], c=y_true[200:], cmap=plt.cm.Spectral)
|
|
||||||
plt.title("ground truth")
|
|
||||||
plt.show()
|
|
||||||
|
|
||||||
plt.scatter(x_test[:, 0], x_test[:, 1], c=y_test_pred, cmap=plt.cm.Spectral)
|
|
||||||
plt.title("predicted")
|
|
||||||
plt.show()
|
|
||||||
|
|
||||||
(loss, acc) = evaluate(NN, y_test_tags)
|
|
||||||
print('--------------------------------')
|
|
||||||
print(f'predict: Loss={loss}, acc={acc}.')
|
|
||||||
@ -1,41 +0,0 @@
|
|||||||
'''
|
|
||||||
Author: SJ2050
|
|
||||||
Date: 2022-01-21 12:01:47
|
|
||||||
LastEditTime: 2022-01-22 11:04:40
|
|
||||||
Version: v0.0.1
|
|
||||||
Description: Full connection multi-layer perceptron using sklearn.
|
|
||||||
Copyright © 2022 SJ2050
|
|
||||||
'''
|
|
||||||
import numpy as np
|
|
||||||
from sklearn.neural_network import MLPClassifier
|
|
||||||
from sklearn.datasets import load_digits
|
|
||||||
from sklearn.metrics import confusion_matrix
|
|
||||||
from sklearn.metrics import accuracy_score
|
|
||||||
import matplotlib.pyplot as plt
|
|
||||||
|
|
||||||
# load data
|
|
||||||
digits = load_digits()
|
|
||||||
X = digits.data
|
|
||||||
Y = digits.target
|
|
||||||
X -= X.min()
|
|
||||||
X /= X.max()
|
|
||||||
|
|
||||||
x_train = X[:-500]
|
|
||||||
y_train = Y[:-500]
|
|
||||||
mlp = MLPClassifier(hidden_layer_sizes=(100), max_iter=10000)
|
|
||||||
mlp.fit(x_train,y_train)
|
|
||||||
|
|
||||||
x_test = X[-500:]
|
|
||||||
y_test = Y[-500:]
|
|
||||||
predictions = mlp.predict(x_test)
|
|
||||||
acc = accuracy_score(y_test, predictions)
|
|
||||||
print('--------------------------------')
|
|
||||||
print(f'predict: acc = {acc}.')
|
|
||||||
|
|
||||||
cm = confusion_matrix(y_test, predictions)
|
|
||||||
plt.matshow(cm)
|
|
||||||
plt.title(u'Confusion Matrix')
|
|
||||||
plt.colorbar()
|
|
||||||
plt.ylabel(u'Groundtruth')
|
|
||||||
plt.xlabel(u'Predict')
|
|
||||||
plt.show()
|
|
||||||
|
Before Width: | Height: | Size: 1.9 MiB |
|
Before Width: | Height: | Size: 51 KiB |
|
Before Width: | Height: | Size: 52 KiB |
|
Before Width: | Height: | Size: 16 KiB |
|
Before Width: | Height: | Size: 15 KiB |
|
Before Width: | Height: | Size: 15 KiB |
File diff suppressed because one or more lines are too long
Binary file not shown.
|
Before Width: | Height: | Size: 6.5 KiB |
|
Before Width: | Height: | Size: 7.3 KiB |
|
Before Width: | Height: | Size: 6.5 KiB |
|
Before Width: | Height: | Size: 117 KiB |
|
Before Width: | Height: | Size: 14 KiB |
Binary file not shown.
Binary file not shown.
Binary file not shown.
File diff suppressed because one or more lines are too long
@ -0,0 +1,57 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Report - 报告题目\n",
|
||||||
|
"\n",
|
||||||
|
"* 姓名\n",
|
||||||
|
"* 学号\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"## 任务简介\n",
|
||||||
|
"\n",
|
||||||
|
"这里简述一下任务是什么；数据的格式，包含了什么数据；最终的目标是什么\n",
|
||||||
|
"\n",
|
||||||
|
"## 解决途径\n",
|
||||||
|
"\n",
|
||||||
|
"主要包括：\n",
|
||||||
|
"1. 问题的思考，整体的思路\n",
|
||||||
|
"2. 选用的方法，以及为何选用这些方法\n",
|
||||||
|
"3. 实现过程遇到的问题，以及如何解决的\n",
|
||||||
|
"4. 最终的结果，实验分析\n",
|
||||||
|
"\n",
|
||||||
|
"要求：\n",
|
||||||
|
"1. 数据的可视化\n",
|
||||||
|
"2. 程序，以及各个部分的解释、说明\n",
|
||||||
|
"3. 结果的可视化，精度等的分析\n",
|
||||||
|
"\n",
|
||||||
|
"## 总结\n",
|
||||||
|
"总结任务实现过程所取得的心得等。"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.5.2"
|
||||||
|
},
|
||||||
|
"main_language": "python"
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 2
|
||||||
|
}
|
||||||
File diff suppressed because one or more lines are too long
Binary file not shown.
|
|
|
|
Before Width: | Height: | Size: 19 KiB |
Binary file not shown.
@ -0,0 +1,57 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Report - 报告题目\n",
|
||||||
|
"\n",
|
||||||
|
"* 姓名\n",
|
||||||
|
"* 学号\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"## 任务简介\n",
|
||||||
|
"\n",
|
||||||
|
"这里简述一下任务是什么；数据的格式，包含了什么数据；最终的目标是什么\n",
|
||||||
|
"\n",
|
||||||
|
"## 解决途径\n",
|
||||||
|
"\n",
|
||||||
|
"主要包括：\n",
|
||||||
|
"1. 问题的思考，整体的思路\n",
|
||||||
|
"2. 选用的方法，以及为何选用这些方法\n",
|
||||||
|
"3. 实现过程遇到的问题，以及如何解决的\n",
|
||||||
|
"4. 最终的结果，实验分析\n",
|
||||||
|
"\n",
|
||||||
|
"要求：\n",
|
||||||
|
"1. 数据的可视化\n",
|
||||||
|
"2. 程序，以及各个部分的解释、说明\n",
|
||||||
|
"3. 结果的可视化，精度等的分析\n",
|
||||||
|
"\n",
|
||||||
|
"## 总结\n",
|
||||||
|
"总结任务实现过程所取得的心得等。"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.5.2"
|
||||||
|
},
|
||||||
|
"main_language": "python"
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 2
|
||||||
|
}
|
||||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 10 KiB |
|
Before Width: | Height: | Size: 8.0 KiB |
|
Before Width: | Height: | Size: 13 KiB |
|
Before Width: | Height: | Size: 7.0 KiB |
|
Before Width: | Height: | Size: 12 KiB |
|
Before Width: | Height: | Size: 9.1 KiB |
|
Before Width: | Height: | Size: 7.2 KiB |
|
Before Width: | Height: | Size: 9.0 KiB |
|
Before Width: | Height: | Size: 14 KiB |
|
Before Width: | Height: | Size: 10 KiB |
|
Before Width: | Height: | Size: 7.7 KiB |
|
Before Width: | Height: | Size: 12 KiB |
|
Before Width: | Height: | Size: 8.8 KiB |
|
Before Width: | Height: | Size: 12 KiB |
|
Before Width: | Height: | Size: 11 KiB |
|
Before Width: | Height: | Size: 9.8 KiB |
|
Before Width: | Height: | Size: 6.8 KiB |
|
Before Width: | Height: | Size: 12 KiB |
|
Before Width: | Height: | Size: 9.9 KiB |
|
Before Width: | Height: | Size: 8.0 KiB |
|
Before Width: | Height: | Size: 9.7 KiB |
|
Before Width: | Height: | Size: 10 KiB |
|
Before Width: | Height: | Size: 6.9 KiB |
|
Before Width: | Height: | Size: 9.3 KiB |
|
Before Width: | Height: | Size: 6.1 KiB |
|
Before Width: | Height: | Size: 9.7 KiB |
|
Before Width: | Height: | Size: 10 KiB |
|
Before Width: | Height: | Size: 6.2 KiB |
|
Before Width: | Height: | Size: 5.1 KiB |
|
Before Width: | Height: | Size: 9.4 KiB |
|
Before Width: | Height: | Size: 6.5 KiB |
|
Before Width: | Height: | Size: 11 KiB |
|
Before Width: | Height: | Size: 13 KiB |
|
Before Width: | Height: | Size: 9.3 KiB |
|
Before Width: | Height: | Size: 9.6 KiB |
|
Before Width: | Height: | Size: 14 KiB |
|
Before Width: | Height: | Size: 5.8 KiB |
|
Before Width: | Height: | Size: 6.5 KiB |
|
Before Width: | Height: | Size: 8.2 KiB |
|
Before Width: | Height: | Size: 9.1 KiB |
|
Before Width: | Height: | Size: 10 KiB |
|
Before Width: | Height: | Size: 12 KiB |
|
Before Width: | Height: | Size: 6.8 KiB |
|
Before Width: | Height: | Size: 8.5 KiB |
|
Before Width: | Height: | Size: 10 KiB |
|
Before Width: | Height: | Size: 11 KiB |
|
Before Width: | Height: | Size: 13 KiB |
|
Before Width: | Height: | Size: 9.7 KiB |
|
Before Width: | Height: | Size: 12 KiB |
|
Before Width: | Height: | Size: 8.5 KiB |
|
Before Width: | Height: | Size: 8.9 KiB |
|
Before Width: | Height: | Size: 6.2 KiB |
|
Before Width: | Height: | Size: 12 KiB |
|
Before Width: | Height: | Size: 6.1 KiB |
|
Before Width: | Height: | Size: 12 KiB |
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue