pxug2blwv
/
machine-learning
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

测试

Browse Source
master
016 2 years ago
parent d42b7f8c8e
commit 7f5a978cc3
8 changed files with 0 additions and 523 deletions
Show Stats Download Patch File Download Diff File

2
README.md
Unescape View File

@ -1,2 +0,0 @@
# machine-learning

136
deep_convnet.py
Unescape View File

@ -1,136 +0,0 @@
# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 为了导入父目录的文件而进行的设定
import pickle
import numpy as np
from collections import OrderedDict
from common.layers import *
class DeepConvNet:
"""识别率为99%以上的高精度的ConvNet
网络结构如下所示
conv - relu - conv- relu - pool -
conv - relu - conv- relu - pool -
conv - relu - conv- relu - pool -
affine - relu - dropout - affine - dropout - softmax
"""
def __init__(self, input_dim=(1, 28, 28),
conv_param_1 = {'filter_num':16, 'filter_size':3, 'pad':1, 'stride':1},
conv_param_2 = {'filter_num':16, 'filter_size':3, 'pad':1, 'stride':1},
conv_param_3 = {'filter_num':32, 'filter_size':3, 'pad':1, 'stride':1},
conv_param_4 = {'filter_num':32, 'filter_size':3, 'pad':2, 'stride':1},
conv_param_5 = {'filter_num':64, 'filter_size':3, 'pad':1, 'stride':1},
conv_param_6 = {'filter_num':64, 'filter_size':3, 'pad':1, 'stride':1},
hidden_size=50, output_size=10):
# 初始化权重===========
# 各层的神经元平均与前一层的几个神经元有连接
pre_node_nums = np.array([1*3*3, 16*3*3, 16*3*3, 32*3*3, 32*3*3, 64*3*3, 64*4*4, hidden_size])
wight_init_scales = np.sqrt(2.0 / pre_node_nums) # 使用ReLU的情况下推荐的初始值
self.params = {}
pre_channel_num = input_dim[0]
for idx, conv_param in enumerate([conv_param_1, conv_param_2, conv_param_3, conv_param_4, conv_param_5, conv_param_6]):
self.params['W' + str(idx+1)] = wight_init_scales[idx] * np.random.randn(conv_param['filter_num'], pre_channel_num, conv_param['filter_size'], conv_param['filter_size'])
self.params['b' + str(idx+1)] = np.zeros(conv_param['filter_num'])
pre_channel_num = conv_param['filter_num']
self.params['W7'] = wight_init_scales[6] * np.random.randn(64*4*4, hidden_size)
self.params['b7'] = np.zeros(hidden_size)
self.params['W8'] = wight_init_scales[7] * np.random.randn(hidden_size, output_size)
self.params['b8'] = np.zeros(output_size)
# 生成层===========
self.layers = []
self.layers.append(Convolution(self.params['W1'], self.params['b1'],
conv_param_1['stride'], conv_param_1['pad']))
self.layers.append(Relu())
self.layers.append(Convolution(self.params['W2'], self.params['b2'],
conv_param_2['stride'], conv_param_2['pad']))
self.layers.append(Relu())
self.layers.append(Pooling(pool_h=2, pool_w=2, stride=2))
self.layers.append(Convolution(self.params['W3'], self.params['b3'],
conv_param_3['stride'], conv_param_3['pad']))
self.layers.append(Relu())
self.layers.append(Convolution(self.params['W4'], self.params['b4'],
conv_param_4['stride'], conv_param_4['pad']))
self.layers.append(Relu())
self.layers.append(Pooling(pool_h=2, pool_w=2, stride=2))
self.layers.append(Convolution(self.params['W5'], self.params['b5'],
conv_param_5['stride'], conv_param_5['pad']))
self.layers.append(Relu())
self.layers.append(Convolution(self.params['W6'], self.params['b6'],
conv_param_6['stride'], conv_param_6['pad']))
self.layers.append(Relu())
self.layers.append(Pooling(pool_h=2, pool_w=2, stride=2))
self.layers.append(Affine(self.params['W7'], self.params['b7']))
self.layers.append(Relu())
self.layers.append(Dropout(0.5))
self.layers.append(Affine(self.params['W8'], self.params['b8']))
self.layers.append(Dropout(0.5))
self.last_layer = SoftmaxWithLoss()
def predict(self, x, train_flg=False):
for layer in self.layers:
if isinstance(layer, Dropout):
x = layer.forward(x, train_flg)
else:
x = layer.forward(x)
return x
def loss(self, x, t):
y = self.predict(x, train_flg=True)
return self.last_layer.forward(y, t)
def accuracy(self, x, t, batch_size=100):
if t.ndim != 1 : t = np.argmax(t, axis=1)
acc = 0.0
for i in range(int(x.shape[0] / batch_size)):
tx = x[i*batch_size:(i+1)*batch_size]
tt = t[i*batch_size:(i+1)*batch_size]
y = self.predict(tx, train_flg=False)
y = np.argmax(y, axis=1)
acc += np.sum(y == tt)
return acc / x.shape[0]
def gradient(self, x, t):
# forward
self.loss(x, t)
# backward
dout = 1
dout = self.last_layer.backward(dout)
tmp_layers = self.layers.copy()
tmp_layers.reverse()
for layer in tmp_layers:
dout = layer.backward(dout)
# 设定
grads = {}
for i, layer_idx in enumerate((0, 2, 5, 7, 10, 12, 15, 18)):
grads['W' + str(i+1)] = self.layers[layer_idx].dW
grads['b' + str(i+1)] = self.layers[layer_idx].db
return grads
def save_params(self, file_name="params.pkl"):
params = {}
for key, val in self.params.items():
params[key] = val
with open(file_name, 'wb') as f:
pickle.dump(params, f)
def load_params(self, file_name="params.pkl"):
with open(file_name, 'rb') as f:
params = pickle.load(f)
for key, val in params.items():
self.params[key] = val
for i, layer_idx in enumerate((0, 2, 5, 7, 10, 12, 15, 18)):
self.layers[layer_idx].W = self.params['W' + str(i+1)]
self.layers[layer_idx].b = self.params['b' + str(i+1)]

159
mnist_cnn_gui_main.py
Unescape View File

@ -1,159 +0,0 @@
import sys
import numpy as np
from PIL import Image, ImageQt
from PyQt5.QtCore import QSize
from PyQt5.QtGui import QPixmap, QColor
from PyQt5.QtWidgets import QMainWindow, QDesktopWidget, QApplication
from PyQt5.QtWidgets import QMessageBox
from common.functions import softmax
from dataset.mnist import load_mnist
from qt.layout import Ui_MainWindow
from qt.paintboard import PaintBoard
from simple_convnet import SimpleConvNet
MODE_WRITE = 2 # 手写输入
Thresh = 0.5 # 识别结果置信度阈值
# 读取MNIST数据集
(_, _), (x_test, _) = load_mnist(normalize=True, flatten=False, one_hot_label=False)
# 初始化网络
# 简单CNN
network = SimpleConvNet(input_dim=(1,28,28),
conv_param = {'filter_num': 30, 'filter_size': 5, 'pad': 0, 'stride': 1},
hidden_size=100, output_size=10, weight_init_std=0.01)
network.load_params("params.pkl")
class MainWindow(QMainWindow,Ui_MainWindow):
def __init__(self):
super(MainWindow,self).__init__()
# 初始化参数
self.result = [0, 0]
# 初始化UI
self.setupUi(self)
self.center()
# 初始化画板
self.paintBoard = PaintBoard(self, Size = QSize(224, 224), Fill = QColor(0,0,0,0))
self.paintBoard.setPenColor(QColor(0,0,0,0))
self.dArea_Layout.addWidget(self.paintBoard)
self.clearDataArea()
# 窗口居中
def center(self):
# 获得窗口
framePos = self.frameGeometry()
# 获得屏幕中心点
scPos = QDesktopWidget().availableGeometry().center()
# 显示到屏幕中心
framePos.moveCenter(scPos)
self.move(framePos.topLeft())
# 窗口关闭事件
def closeEvent(self, event):
reply = QMessageBox.question(self, '消息',
"确定退出吗?", QMessageBox.Yes |
QMessageBox.No, QMessageBox.Yes)
if reply == QMessageBox.Yes:
event.accept()
else:
event.ignore()
# 清除数据待输入区
def clearDataArea(self):
self.paintBoard.Clear()
self.lbDataArea.clear()
self.lbResult.clear()
self.lbCofidence.clear()
self.result = [0, 0]
"""
回调函数
"""
# 模式下拉列表回调
def cbBox_Mode_Callback(self, text):
self.mode = MODE_WRITE
self.clearDataArea()
# 更改背景
self.paintBoard.setBoardFill(QColor(0,0,0,255))
self.paintBoard.setPenColor(QColor(255,255,255,255))
# 数据清除
def pbtClear_Callback(self):
self.clearDataArea()
# 识别
def pbtPredict_Callback(self):
__img = self.paintBoard.getContentAsQImage()
# 转换成pil image类型处理
pil_img = ImageQt.fromqimage(__img)
pil_img = pil_img.resize((28, 28), Image.ANTIALIAS)
img_array = np.array(pil_img.convert('L')).reshape(1,1,28, 28) / 255.0
# img_array = np.where(img_array>0.5, 1, 0)
# reshape成网络输入类型
__result = network.predict(img_array) # shape:[1, 10]
# print (__result)
# 将预测结果使用softmax输出
__result = softmax(__result)
self.result[0] = np.argmax(__result) # 预测的数字
self.result[1] = __result[0, self.result[0]] # 置信度
self.lbResult.setText("%d" % (self.result[0]))
self.lbCofidence.setText("%.8f" % (self.result[1]))
# # 随机抽取
# def pbtGetMnist_Callback(self):
# self.clearDataArea()
#
# # 随机抽取一张测试集图片，放大后显示
# img = x_test[np.random.randint(0, 9999)] # shape:[1,28,28]
# img = img.reshape(28, 28) # shape:[28,28]
#
# img = img * 0xff # 恢复灰度值大小
# pil_img = Image.fromarray(np.uint8(img))
# pil_img = pil_img.resize((224, 224)) # 图像放大显示
#
# # 将pil图像转换成qimage类型
# qimage = ImageQt.ImageQt(pil_img)
#
# # 将qimage类型图像显示在label
# pix = QPixmap.fromImage(qimage)
# self.lbDataArea.setPixmap(pix)
#
if __name__ == "__main__":
app = QApplication(sys.argv)
Gui = MainWindow()
Gui.show()
sys.exit(app.exec_())

BIN
params.pkl
View File

Binary file not shown.

160
simple_convnet.py
Unescape View File

@ -1,160 +0,0 @@
# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 为了导入父目录的文件而进行的设定
import pickle
import numpy as np
from collections import OrderedDict
from common.layers import *
from common.gradient import numerical_gradient
class SimpleConvNet:
"""简单的ConvNet
conv - relu - pool - affine - relu - affine - softmax
Parameters
----------
input_size : 输入大小（MNIST的情况下为784）
hidden_size_list : 隐藏层的神经元数量的列表（e.g. [100, 100, 100]）
output_size : 输出大小（MNIST的情况下为10）
activation : 'relu' or 'sigmoid'
weight_init_std : 指定权重的标准差（e.g. 0.01）
指定'relu'或'he'的情况下设定“He的初始值”
指定'sigmoid'或'xavier'的情况下设定“Xavier的初始值”
"""
def __init__(self, input_dim=(1, 28, 28),
conv_param={'filter_num':30, 'filter_size':5, 'pad':0, 'stride':1},
hidden_size=100, output_size=10, weight_init_std=0.01):
filter_num = conv_param['filter_num']
filter_size = conv_param['filter_size']
filter_pad = conv_param['pad']
filter_stride = conv_param['stride']
input_size = input_dim[1]
conv_output_size = (input_size - filter_size + 2*filter_pad) / filter_stride + 1
pool_output_size = int(filter_num * (conv_output_size/2) * (conv_output_size/2))
# 初始化权重
self.params = {}
self.params['W1'] = weight_init_std * \
np.random.randn(filter_num, input_dim[0], filter_size, filter_size)
self.params['b1'] = np.zeros(filter_num)
self.params['W2'] = weight_init_std * \
np.random.randn(pool_output_size, hidden_size)
self.params['b2'] = np.zeros(hidden_size)
self.params['W3'] = weight_init_std * \
np.random.randn(hidden_size, output_size)
self.params['b3'] = np.zeros(output_size)
# 生成层
self.layers = OrderedDict()
self.layers['Conv1'] = Convolution(self.params['W1'], self.params['b1'],
conv_param['stride'], conv_param['pad'])
self.layers['Relu1'] = Relu()
self.layers['Pool1'] = Pooling(pool_h=2, pool_w=2, stride=2)
self.layers['Affine1'] = Affine(self.params['W2'], self.params['b2'])
self.layers['Relu2'] = Relu()
self.layers['Affine2'] = Affine(self.params['W3'], self.params['b3'])
self.last_layer = SoftmaxWithLoss()
def predict(self, x):
for layer in self.layers.values():
x = layer.forward(x)
return x
def loss(self, x, t):
"""求损失函数
参数x是输入数据、t是教师标签
"""
y = self.predict(x)
return self.last_layer.forward(y, t)
def accuracy(self, x, t, batch_size=100):
if t.ndim != 1 : t = np.argmax(t, axis=1)
acc = 0.0
for i in range(int(x.shape[0] / batch_size)):
tx = x[i*batch_size:(i+1)*batch_size]
tt = t[i*batch_size:(i+1)*batch_size]
y = self.predict(tx)
y = np.argmax(y, axis=1)
acc += np.sum(y == tt)
return acc / x.shape[0]
def numerical_gradient(self, x, t):
"""求梯度（数值微分）
Parameters
----------
x : 输入数据
t : 教师标签
Returns
-------
具有各层的梯度的字典变量
grads['W1']、grads['W2']、...是各层的权重
grads['b1']、grads['b2']、...是各层的偏置
"""
loss_w = lambda w: self.loss(x, t)
grads = {}
for idx in (1, 2, 3):
grads['W' + str(idx)] = numerical_gradient(loss_w, self.params['W' + str(idx)])
grads['b' + str(idx)] = numerical_gradient(loss_w, self.params['b' + str(idx)])
return grads
def gradient(self, x, t):
"""求梯度（误差反向传播法）
Parameters
----------
x : 输入数据
t : 教师标签
Returns
-------
具有各层的梯度的字典变量
grads['W1']、grads['W2']、...是各层的权重
grads['b1']、grads['b2']、...是各层的偏置
"""
# forward
self.loss(x, t)
# backward
dout = 1
dout = self.last_layer.backward(dout)
layers = list(self.layers.values())
layers.reverse()
for layer in layers:
dout = layer.backward(dout)
# 设定
grads = {}
grads['W1'], grads['b1'] = self.layers['Conv1'].dW, self.layers['Conv1'].db
grads['W2'], grads['b2'] = self.layers['Affine1'].dW, self.layers['Affine1'].db
grads['W3'], grads['b3'] = self.layers['Affine2'].dW, self.layers['Affine2'].db
return grads
def save_params(self, file_name="params.pkl"):
params = {}
for key, val in self.params.items():
params[key] = val
with open(file_name, 'wb') as f:
pickle.dump(params, f)
def load_params(self, file_name="params.pkl"):
with open(file_name, 'rb') as f:
params = pickle.load(f)
for key, val in params.items():
self.params[key] = val
for i, key in enumerate(['Conv1', 'Affine1', 'Affine2']):
self.layers[key].W = self.params['W' + str(i+1)]
self.layers[key].b = self.params['b' + str(i+1)]

1
test.py
Unescape View File

@ -1 +0,0 @@
print("hello word")

44
train_convnet.py
Unescape View File

@ -1,44 +0,0 @@
# coding: utf-8
import os
import sys
sys.path.append(os.pardir) # 为了导入父目录的文件而进行的设定
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from simple_convnet import SimpleConvNet
from common.trainer import Trainer
# 读入数据
(x_train, t_train), (x_test, t_test) = load_mnist(flatten=False)
# 处理花费时间较长的情况下减少数据
# x_train, t_train = x_train[:5000], t_train[:5000]
# x_test, t_test = x_test[:1000], t_test[:1000]
max_epochs = 5
network = SimpleConvNet(input_dim=(1, 28, 28),
conv_param={'filter_num': 30, 'filter_size': 5, 'pad': 0, 'stride': 1},
hidden_size=100, output_size=10, weight_init_std=0.01)
trainer = Trainer(network, x_train, t_train, x_test, t_test,
epochs=max_epochs, mini_batch_size=100,
optimizer='Adam', optimizer_param={'lr': 0.001},
evaluate_sample_num_per_epoch=1000)
trainer.train()
# 保存参数
network.save_params("params.pkl")
print("Saved Network Parameters!")
# 绘制图形
markers = {'train': 'o', 'test': 's'}
x = np.arange(max_epochs)
plt.plot(x, trainer.train_acc_list, marker='o', label='train', markevery=2)
plt.plot(x, trainer.test_acc_list, marker='s', label='test', markevery=2)
plt.xlabel("epochs")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()

21
train_deepnet.py
Unescape View File

@ -1,21 +0,0 @@
# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 为了导入父目录而进行的设定
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from deep_convnet import DeepConvNet
from common.trainer import Trainer
(x_train, t_train), (x_test, t_test) = load_mnist(flatten=False)
network = DeepConvNet()
trainer = Trainer(network, x_train, t_train, x_test, t_test,
epochs=5, mini_batch_size=100,
optimizer='Adam', optimizer_param={'lr':0.001},
evaluate_sample_num_per_epoch=1000)
trainer.train()
# 保存参数
network.save_params("deep_convnet_params.pkl")
print("Saved Network Parameters!")
Write Preview
Loading…
Cancel
Save