tf dense layer两种创建方式的对比和numpy实现

文章目录

• • 1 Dense Layer
  • 2 对比原始的add layer方法和继承方法的不同
  • • 2.1 global config
    • 2.1 用add实现
    • 2.2 用继承实现
  • 3 有权重的对比
  • • 3.1 用自带add_weight方法自定义权重
    • 3.2 用add实现
    • 3.3 用继承实现
  • 4 用自定义矩阵为权重矩阵
  • • 4.1 初始化权重和偏移项矩阵
    • 4.2 用add实现
    • 4.3 用继承实现
  • 5 用numpy实现
  • • 5.1 初始化权重和偏移项矩阵
    • 5.2 add实现，有激活函数
    • 5.3 tf 实现
    • 5.4 numpy实现

1 Dense Layer

目的：构建Dense层，对比两种方法实现的区别

2 对比原始的add layer方法和继承方法的不同

2.1 global config

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.layers import Input, LSTM, Dense
import numpy as npnp.random.seed(1)rows = 10000  	# 样本数
columns = 100	# 特征数train_x1 = np.random.random(size=(int(rows/2), columns))
train_y1 = np.random.choice([0], size=(int(rows/2), 1))
train_x2 = np.random.random(size=(int(rows/2), columns))+1
train_y2 = np.random.choice([1], size=(int(rows/2), 1))train_x = np.vstack((train_x1, train_x2))
train_y = np.vstack((train_y1, train_y2))units = 5	# 自定义cell个数

2.1 用add实现

tf.random.set_seed(1)		# 固定随机值model1 = keras.Sequential()
model1.add(Input(shape=(columns,)))
model1.add(Dense(units=units))model1.compile(optimizer="adam", loss="mse", metrics=["accuracy"])model1.fit(train_x, train_y, epochs=10)
model1.predict(train_x)[-1][-1]l1 = model1.layers[0]
w1, b1 = l1.get_weights()

api中的参数分几部分

1. initializer 初始项，初始化参数
2. regularizer 正则项，选择不同正则模式L1L2
3. constraint 约束项，非负约束或者最大模约束

2.2 用继承实现

tf.random.set_seed(1)		# 固定随机值class MyDenseLayer(keras.layers.Layer):def __init__(self, num_outputs):super(MyDenseLayer, self).__init__()self.num_outputs = num_outputsdef build(self, input_shape):self.kernel = self.add_weight(name="kernel", shape=[int(input_shape[-1]), self.num_outputs])self.bias = self.add_weight(name="bias", shape=[self.num_outputs, ], initializer=keras.initializers.zeros)self.build = Truedef call(self, input):return tf.matmul(input, self.kernel) + self.biasmodel2 = keras.Sequential()
model2.add(Input(shape=(columns,)))
model2.add(MyDenseLayer(units))		model2.compile(loss="mse", optimizer="adam", metrics=['accuracy'])model2.fit(train_x, train_y, epochs=10)
model2.predict(train_x)[-1][-1]l2 = model2.layers[0]
w2, b2 = l2.get_weights()

3 有权重的对比

3.1 用自带add_weight方法自定义权重

自定义初始的权重和偏移项。为什么要定义这两个方法？为了用add_weight方法初始权重和偏移项

def w_init(shape, dtype=tf.float32):return tf.random.normal(shape=shape, dtype=dtype)def b_init(shape, dtype=tf.float32):return tf.zeros(shape=shape, dtype=dtype)

3.2 用add实现

tf.random.set_seed(1)		# 固定随机值model3 = keras.Sequential()
model3.add(Input(shape=(columns,)))
model3.add(Dense(units=units, kernel_initializer=w_init, bias_initializer=b_init))	# 需要固定weightsmodel3.compile(optimizer="adam", loss="mse", metrics=["accuracy"])model3.fit(train_x, train_y, epochs=10)
model3.predict(train_x)[-1][-1]l3 = model3.layers[0]
w3, b3 = l3.get_weights()

3.3 用继承实现

tf.random.set_seed(1)		# 固定随机值class MyDenseLayer(keras.layers.Layer):def __init__(self, num_outputs):super(MyDenseLayer, self).__init__()self.num_outputs = num_outputsdef build(self, input_shape):self.kernel = self.add_weight(initializer=w_init, shape=(input_shape[-1], self.num_outputs), dtype=tf.float32)	# 自定义权重self.bias = self.add_weight(initializer=b_init, shape=(self.num_outputs,), dtype=tf.float32)		# 自定义偏移项def call(self, input):return tf.matmul(input, self.kernel) + self.biasmodel4 = keras.Sequential()
model4.add(Input(shape=(columns,)))
model4.add(MyDenseLayer(units))		model4.compile(loss="mse", optimizer="adam", metrics=['accuracy'])model4.fit(train_x, train_y, epochs=10)
model4.predict(train_x)[-1][-1]l4 = model4.layers[0]
w4, b4 = l4.get_weights()

4 用自定义矩阵为权重矩阵

4.1 初始化权重和偏移项矩阵

tf.random.set_seed(1)
w = tf.random.normal(shape=(columns, units), dtype=tf.float32)
b = tf.zeros(shape=(units,), dtype=tf.float32)def w_init(shape, dtype=tf.float32):return wdef b_init(shape, dtype=tf.float32):return b

4.2 用add实现

tf.random.set_seed(1)		# 固定随机值model5 = keras.Sequential()
model5.add(Input(shape=(columns,)))
model5.add(Dense(units=units, kernel_initializer=w_init, bias_initializer=b_init))		model5.compile(loss="mse", optimizer="adam", metrics=['accuracy'])model5.fit(train_x, train_y, epochs=10)
model5.predict(train_x)[-1][-1]

4.3 用继承实现

不用Layer.add_weight方法，自己实现一个权重矩阵，然后用权重矩阵作为初始化，进行训练

tf.random.set_seed(1)		# 固定随机值class MyDenseLayer(keras.layers.Layer):def __init__(self, num_outputs):super(MyDenseLayer, self).__init__()self.num_outputs = num_outputsdef build(self, input_shape):self.kernel = tf.Variable(w, trainable=True)self.bias = tf.Variable(b, trainable=True)def call(self, input):return tf.matmul(input, self.kernel) + self.biasmodel6 = keras.Sequential()
model6.add(Input(shape=(columns,)))
model6.add(MyDenseLayer(units))		model6.compile(loss="mse", optimizer="adam", metrics=['accuracy'])model6.fit(train_x, train_y, epochs=10)
model6.predict(train_x)[-1][-1]

5 用numpy实现

5.1 初始化权重和偏移项矩阵

tf.random.set_seed(1)train_x = np.ones(shape=(rows, columns), dtype="float32")	# 这里一定要dtype一致，否则numpy与keras计算结果会有差异，我这里统一使用float32
train_y = np.vstack([np.ones(shape=(int(rows/2), 1), dtype="float32"), np.zeros(shape=(int(rows/2),1), dtype="float32")])w = tf.random.normal(shape=(columns, 1), dtype=tf.float32)
b = tf.zeros(shape=(1,), dtype=tf.float32)def w_init(shape, dtype=tf.float32):return tf.convert_to_tensor(w, dtype=tf.float32)def b_init(shape, dtype=tf.float32):return tf.convert_to_tensor(b, dtype=tf.float32)

5.2 add实现，有激活函数

tf.random.set_seed(1)		# 固定随机值model7 = keras.Sequential()
model7.add(Input(shape=(columns,)))
model7.add(Dense(units=1, kernel_initializer=w_init, bias_initializer=b_init, activation="sigmoid"))h1 = model7.predict(train_x)model7.compile(loss="mse", optimizer=tf.keras.optimizers.SGD(learning_rate=learning_rate), metrics=['accuracy'])model7.fit(train_x, train_y, epochs=1, batch_size=rows)	#这里要注意batch_size要用BatchGD，因为numpy实现时没有用batch，用的是全量数据更新w1, b1 = model7.layers[0].weights

5.3 tf 实现

tf.random.set_seed(1)		# 固定随机值x = tf.Variable(train_x, dtype=tf.float32)
w2 = w
b2 = b
with tf.GradientTape(persistent=True) as tape:tape.watch([w2, b2])y_pred = 1/(1+tf.math.exp(-1*tf.matmul(x, w2)+b2))loss = tf.math.reduce_mean(tf.math.square(tf.subtract(y_pred, train_y)))dw2 = tape.gradient(target=loss, sources=w2)
db2 = tape.gradient(target=loss, sources=b2)w2 = w2 - dw2*learning_rate
b2 = b2 - db2*learning_rate

5.4 numpy实现

import numpy as npclass MyModel:def __init__(self, w, b, learning_rate):self.w = wself.b = bself.learning_rate = learning_ratedef fit(self, train_x, train_y, epochs, batch_size):self.x = train_xself.y = train_yfor epoch in range(epochs):print(f"epoch {epoch}")self.forward()  # 正向传播self.get_loss()self.backward()def forward(self):self.h3 = self.sigmoid(np.dot(self.x, self.w) + self.b)def backward(self):learning_rate = 0.01dw3 = np.dot(self.x.T, 2*(self.h3 - self.y)*self.h3*(1-self.h3)/train_x.shape[0])  # loss对w的求导db3 = np.dot(np.ones(shape=(1, rows)), 2*(self.h3 - self.y)*self.h3*(1-self.h3)/train_x.shape[0])  # loss对b的求导self.w -= dw3 * learning_rateself.b -= db3 * learning_ratedef sigmoid(self, x):return 1 / (1 + np.exp(-x))def get_loss(self):loss = np.sum((np.square(self.h3-self.y)), axis=0)/rowsprint(f"loss {loss}")def predict(self):passmodel8 = MyModel(w, b, learning_rate)
model8.fit(train_x, train_y, epochs=1, batch_size=rows)w3 = model8.w
b3 = model8.b

本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！