代码来源：https://github.com/eriklindernoren/ML-From-Scratch
卷积神经网络中卷积层Conv2D（带stride、padding）的具体实现：https://www.cnblogs.com/xiximayou/p/12706576.html
激活函数的实现（sigmoid、softmax、tanh、relu、leakyrelu、elu、selu、softplus）：https://www.cnblogs.com/xiximayou/p/12713081.html
损失函数定义（均方误差、交叉熵损失）：https://www.cnblogs.com/xiximayou/p/12713198.html
优化器的实现（SGD、Nesterov、Adagrad、Adadelta、RMSprop、Adam）：https://www.cnblogs.com/xiximayou/p/12713594.html
卷积层反向传播过程：https://www.cnblogs.com/xiximayou/p/12713930.html
全连接层实现：https://www.cnblogs.com/xiximayou/p/12720017.html
批量归一化层实现：https://www.cnblogs.com/xiximayou/p/12720211.html
池化层实现：https://www.cnblogs.com/xiximayou/p/12720324.html
padding2D实现：https://www.cnblogs.com/xiximayou/p/12720454.html
Flatten层实现：https://www.cnblogs.com/xiximayou/p/12720518.html
上采样层UpSampling2D实现：https://www.cnblogs.com/xiximayou/p/12720558.html
Dropout层实现：https://www.cnblogs.com/xiximayou/p/12720589.html
激活层实现：https://www.cnblogs.com/xiximayou/p/12720622.html
首先是所有的代码：
from __future__ import print_function, division
from terminaltables import AsciiTable
import numpy as np
import progressbar
from mlfromscratch.utils import batch_iterator
from mlfromscratch.utils.misc import bar_widgetsclass NeuralNetwork():
"""Neural Network. Deep Learning base model.
Parameters:
-----------
optimizer: class
The weight optimizer that will be used to tune the weights in order of minimizing
the loss.
loss: class
Loss function used to measure the model's performance. SquareLoss or CrossEntropy.
validation: tuple
A tuple containing validation data and labels (X, y)
"""
def __init__(self, optimizer, loss, validation_data=None):
self.optimizer = optimizer
self.layers = []
self.errors = {"training": [], "validation": []}
self.loss_function = loss()
self.progressbar = progressbar.ProgressBar(widgets=bar_widgets) self.val_set = None
if validation_data:
X, y = validation_data
self.val_set = {"X": X, "y": y} def set_trainable(self, trainable):
""" Method which enables freezing of the weights of the network's layers. """
for layer in self.layers:
layer.trainable = trainable def add(self, layer):
""" Method which adds a layer to the neural network """
# If this is not the first layer added then set the input shape
# to the output shape of the last added layer
if self.layers:
layer.set_input_shape(shape=self.layers[-1].output_shape()) # If the layer has weights that needs to be initialized
if hasattr(layer, 'initialize'):
layer.initialize(optimizer=self.optimizer) # Add layer to the network
self.layers.append(layer) def test_on_batch(self, X, y):
""" Evaluates the model over a single batch of samples """
y_pred = self._forward_pass(X, training=False)
loss = np.mean(self.loss_function.loss(y, y_pred))
acc = self.loss_function.acc(y, y_pred) return loss, acc def train_on_batch(self, X, y):
""" Single gradient update over one batch of samples """
y_pred = self._forward_pass(X)
loss = np.mean(self.loss_function.loss(y, y_pred))
acc = self.loss_function.acc(y, y_pred)
# Calculate the gradient of the loss function wrt y_pred
loss_grad = self.loss_function.gradient(y, y_pred)
# Backpropagate. Update weights
self._backward_pass(loss_grad=loss_grad) return loss, acc def fit(self, X, y, n_epochs, batch_size):
""" Trains the model for a fixed number of epochs """
for _ in self.progressbar(range(n_epochs)): batch_error = []
for X_batch, y_batch in batch_iterator(X, y, batch_size=batch_size):
loss, _ = self.train_on_batch(X_batch, y_batch)
batch_error.append(loss) self.errors["training"].append(np.mean(batch_error)) if self.val_set is not None:
val_loss, _ = self.test_on_batch(self.val_set["X"], self.val_set["y"])
self.errors["validation"].append(val_loss) return self.errors["training"], self.errors["validation"] def _forward_pass(self, X, training=True):
""" Calculate the output of the NN """
layer_output = X
for layer in self.layers:
layer_output = layer.forward_pass(layer_output, training) return layer_output def _backward_pass(self, loss_grad):
""" Propagate the gradient 'backwards' and update the weights in each layer """
for layer in reversed(self.layers):
loss_grad = layer.backward_pass(loss_grad) def summary(self, name="Model Summary"):
# Print model name
print (AsciiTable([[name]]).table)
# Network input shape (first layer's input shape)
print ("Input Shape: %s" % str(self.layers[0].input_shape))
# Iterate through network and get each layer's configuration
table_data = [["Layer Type", "Parameters", "Output Shape"]]
tot_params = 0
for layer in self.layers:
layer_name = layer.layer_name()
params = layer.parameters()
out_shape = layer.output_shape()
table_data.append([layer_name, str(params), str(out_shape)])
tot_params += params
# Print network configuration table
print (AsciiTable(table_data).table)
print ("Total Parameters: %d\n" % tot_params) def predict(self, X):
""" Use the trained model to predict labels of X """
return self._forward_pass(X, training=False)
接着我们来一个一个函数进行分析：
1、初始化__init__：这里面定义好优化器optimizer、模型层layers、错误errors、损失函数loss_function、用于显示进度条progressbar，这里从mlfromscratch.utils.misc中导入了bar_widgets，我们看看这是什么：
bar_widgets = [
'Training: ', progressbar.Percentage(), ' ', progressbar.Bar(marker="-", left="[", right="]"),
' ', progressbar.ETA()
]
2、set_trainable()：用于设置哪些模型层需要进行参数的更新
3、add()：将一个模块放入到卷积神经网络中，例如卷积层、池化层、激活层等等。
4、test_on_batch()：使用batch进行测试，这里不需要进行反向传播。
5、train_on_batch()：使用batch进行训练，包括前向传播计算损失以及反向传播更新参数。
6、fit()：喂入数据进行训练或验证，这里需要定义好epochs和batch_size的大小，同时有一个读取数据的函数batch_iterator()，位于mlfromscratch.utils下的data_manipulation.py中：
def batch_iterator(X, y=None, batch_size=64):
""" Simple batch generator """
n_samples = X.shape[0]
for i in np.arange(0, n_samples, batch_size):
begin, end = i, min(i+batch_size, n_samples)
if y is not None:
yield X[begin:end], y[begin:end]
else:
yield X[begin:end]
7、_forward_pass()：模型层的前向传播。
8、_backward_pass()：模型层的反向传播。
9、summary()：用于输出模型的每层的类型、参数数量以及输出大小。
10、predict()：用于输出预测值。
不难发现，该代码是借鉴了tensorflow中的一些模块的设计思想。
