master
016
2 years ago
parent
d42b7f8c8e
commit
7f5a978cc3
@ -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)]
|
||||
@ -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_())
|
||||
Binary file not shown.
@ -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()
|
||||
@ -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!")
|
||||
Loading…
Reference in new issue