may be last version

By completing the thesis, we have corrected the deficiencies and fixed some bugs.

Number-Of-Pool/_mian_tensorflow_Four_PoolCNN.py

@@ -6,7 +6,7 @@ import pywt
 import wfdb
 import tensorflow as tf
 from tensorflow import keras
-from utils_two_of_PoolCNN import loadData, plot_history_tf, plot_heat_map
+from utils_four_of_PoolCNN import loadData, plot_history_tf, plot_heat_map
 
 #from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH
 #PATH of this test

Number-Of-Pool/_mian_tensorflow_One_PoolCNN.py

@@ -6,7 +6,7 @@ import pywt
 import wfdb
 import tensorflow as tf
 from tensorflow import keras
-from utils_two_of_PoolCNN import loadData, plot_history_tf, plot_heat_map
+from utils_one_of_PoolCNN import loadData, plot_history_tf, plot_heat_map
 
 #from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH
 #PATH of this test

Number-Of-Pool/_mian_tensorflow_Three_PoolCNN.py

@@ -6,7 +6,7 @@ import pywt
 import wfdb
 import tensorflow as tf
 from tensorflow import keras
-from utils_two_of_PoolCNN import loadData, plot_history_tf, plot_heat_map
+from utils_three_of_PoolCNN import loadData, plot_history_tf, plot_heat_map
 
 #from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH
 #PATH of this test

Number_Of_Filters/_mian_tensorflow_SeventyOne_Filters.py

@@ -31,11 +31,11 @@ def CNN_model_level_one():
         tf.keras.layers.InputLayer(input_shape=(300,)),
         tf.keras.layers.Reshape(target_shape=(300, 1)),
 
-        tf.keras.layers.Conv1D(filters=3, kernel_size=3, strides=2, padding='same', activation='relu'),
+        tf.keras.layers.Conv1D(filters=71, kernel_size=3, strides=2, padding='same', activation='relu'),
         tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'),
-        tf.keras.layers.Conv1D(filters=3, kernel_size=3, strides=2, padding='same', activation='relu'),
+        tf.keras.layers.Conv1D(filters=71, kernel_size=3, strides=2, padding='same', activation='relu'),
         tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'),
-        tf.keras.layers.Conv1D(filters=3, kernel_size=3, strides=2, padding='same', activation='relu'),
+        tf.keras.layers.Conv1D(filters=71, kernel_size=3, strides=2, padding='same', activation='relu'),
         tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'),
 
         tf.keras.layers.Flatten(),

The_last_model/utils_CNN_of_ECG.py

@@ -33,7 +33,6 @@ def denoise(date):
         coeffs[i] = pywt.threshold(coeffs[i], threshold)
     # get signal that before wavelet
     rdata = pywt.waverec(coeffs=coeffs, wavelet='db5')
-    return rdata
 
 
 # get ECG data,date type and denoise

some-test/activation.py

@@ -0,0 +1,44 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Sun Mar 11 20:41:57 2018
+
+@author: brucelau
+"""
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+x = np.linspace(-10,10)
+y_sigmoid = 1/(1+np.exp(-x))
+y_tanh = (np.exp(x)-np.exp(-x))/(np.exp(x)+np.exp(-x))
+
+fig = plt.figure()
+# plot sigmoid
+ax = fig.add_subplot(221)
+ax.plot(x,y_sigmoid)
+ax.grid()
+ax.set_title('(a) Sigmoid')
+
+# plot tanh
+ax = fig.add_subplot(222)
+ax.plot(x,y_tanh)
+ax.grid()
+ax.set_title('(b) Tanh')
+
+# plot relu
+ax = fig.add_subplot(223)
+y_relu = np.array([0*item  if item<0 else item for item in x ])
+ax.plot(x,y_relu)
+ax.grid()
+ax.set_title('(c) ReLu')
+
+#plot leaky relu
+ax = fig.add_subplot(224)
+y_relu = np.array([0.2*item  if item<0 else item for item in x ])
+ax.plot(x,y_relu)
+ax.grid()
+ax.set_title('(d) Leaky ReLu')
+
+plt.tight_layout()
+plt.show()
+

some-test/db5.py

@@ -0,0 +1,29 @@
+import pywt
+import matplotlib.pyplot as plt
+
+# 生成DB5小波
+wavelet = pywt.Wavelet('db5')
+
+# 获取尺度函数和小波函数
+phi, psi, x = wavelet.wavefun(level=5)
+
+# 绘制尺度函数和小波函数
+plt.figure()
+plt.subplot(2, 1, 1)
+plt.plot(x, phi)
+plt.title('DB5 Scaling Function (Phi)')
+plt.subplot(2, 1, 2)
+plt.plot(x, psi)
+plt.title('DB5 Wavelet Function (Psi)')
+plt.tight_layout()
+plt.show()
+
+h0=wavelet.dec_lo
+h1=wavelet.dec_hi
+g0=wavelet.rec_lo
+g1=wavelet.rec_hi
+
+print('h0:', h0)
+print('h1:', h1)
+print('g0:', g0)
+print('g1:', g1)

some-test/keras_use.py

@@ -0,0 +1,36 @@
+import numpy as np
+import keras
+from keras.models import Sequential
+from keras.layers import Dense, Dropout, Flatten
+from keras.layers import Conv2D, MaxPooling2D
+from keras.optimizers import SGD
+
+# 生成虚拟数据
+x_train = np.random.random((100, 100, 100, 3))
+y_train = keras.utils.to_categorical(np.random.randint(10, size=(100, 1)), num_classes=10)
+x_test = np.random.random((20, 100, 100, 3))
+y_test = keras.utils.to_categorical(np.random.randint(10, size=(20, 1)), num_classes=10)
+
+model = Sequential()
+# 输入: 3 通道 100x100 像素图像 -> (100, 100, 3) 张量。
+# 使用 32 个大小为 3x3 的卷积滤波器。
+model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(100, 100, 3)))
+model.add(Conv2D(32, (3, 3), activation='relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+model.add(Dropout(0.25))
+
+model.add(Conv2D(64, (3, 3), activation='relu'))
+model.add(Conv2D(64, (3, 3), activation='relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+model.add(Dropout(0.25))
+
+model.add(Flatten())
+model.add(Dense(256, activation='relu'))
+model.add(Dropout(0.5))
+model.add(Dense(10, activation='softmax'))
+
+sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
+model.compile(loss='categorical_crossentropy', optimizer=sgd)
+
+model.fit(x_train, y_train, batch_size=32, epochs=10)
+score = model.evaluate(x_test, y_test, batch_size=32)

some-test/softmax.py

@@ -0,0 +1,14 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+def softmax(x):
+    return np.exp(x) / np.sum(np.exp(x))
+
+x = np.arange(-10, 10, 0.1)
+y = softmax(x)
+
+plt.plot(x, y)
+plt.title('Softmax Function')
+plt.xlabel('Input')
+plt.ylabel('Output')
+plt.show()