在前面一篇文章《python分模块实现神经网络之CIFARF分类:1.加载CIFAR数据集》中,我们已经加载了数据集,下面我们来定义神经网络架构。
定义神经网路架构由fc_net.py layer_utils.py layer.py三个文件共同完成,
fc_net.py中定义了TwoLayerNet类,TwoLayerNet类中包括__init__()和loss()两个函数,__init__()用于初始化神经网络参数,loss()对神经网络进行前向传播和反向传播,该文件的具体代码如下:
from layer_utils import *
import numpy as np
class TwoLayerNet(object):
def __init__(self, input_dim=3*32*32, hidden_dim=100, num_classes=10,
weight_scale=1e-3, reg=0.0):
"""
Initialize a new network.
Inputs:
- input_dim: An integer giving the size of the input
- hidden_dim: An integer giving the size of the hidden layer
- num_classes: An integer giving the number of classes to classify
- dropout: Scalar between 0 and 1 giving dropout strength.
- weight_scale: Scalar giving the standard deviation for random
initialization of the weights.
- reg: Scalar giving L2 regularization strength.
"""
self.params = {}
self.reg = reg
self.params['W1'] = weight_scale * np.random.randn(input_dim, hidden_dim)
self.params['b1'] = np.zeros((1, hidden_dim))
self.params['W2'] = weight_scale * np.random.randn(hidden_dim, num_classes)
self.params['b2'] = np.zeros((1, num_classes))
def loss(self, X, y=None):
"""
Compute loss and gradient for a minibatch of data.
Inputs:
- X: Array of input data of shape (N, d_1, ..., d_k)
- y: Array of labels, of shape (N,). y[i] gives the label for X[i].
Returns:
If y is None, then run a test-time forward pass of the model and return:
- scores: Array of shape (N, C) giving classification scores, where
scores[i, c] is the classification score for X[i] and class c.
If y is not None, then run a training-time forward and backward pass and
return a tuple of:
- loss: Scalar value giving the loss
- grads: Dictionary with the same keys as self.params, mapping parameter
names to gradients of the loss with respect to those parameters.
"""
scores = None
N = X.shape[0]
# Unpack variables from the params dictionary
W1, b1 = self.params['W1'], self.params['b1']
W2, b2 = self.params['W2'], self.params['b2']
h1, cache1 = affine_relu_forward(X, W1, b1)
out, cache2 = affine_forward(h1, W2, b2)
scores = out # (N,C)
# If y is None then we are in test mode so just return scores
if y is None:
return scores
loss, grads = 0, {}
data_loss, dscores = softmax_loss(scores, y)
reg_loss = 0.5 * self.reg * np.sum(W1*W1) + 0.5 * self.reg * np.sum(W2*W2)
loss = data_loss + reg_loss
# Backward pass: compute gradients
dh1, dW2, db2 = affine_backward(dscores, cache2)
dX, dW1, db1 = affine_relu_backward(dh1, cache1)
# Add the regularization gradient contribution
dW2 += self.reg * W2
dW1 += self.reg * W1
grads['W1'] = dW1
grads['b1'] = db1
grads['W2'] = dW2
grads['b2'] = db2
return loss, grads
fc_net中调用了layer_utils.py和layers.py中的函数,从fc_net代码中第一行可以看出,fc_net需要导入layer_utils.py。layer_utils.py是对layers.py的进一步封装,layers.py中主要包括每层神经元的前向传播函数和反向传播函数。
layer_utils.py
from layers import *
def affine_relu_forward(x, w, b):
"""
Convenience layer that perorms an affine transform followed by a ReLU
Inputs:
- x: Input to the affine layer
- w, b: Weights for the affine layer
Returns a tuple of:
- out: Output from the ReLU
- cache: Object to give to the backward pass
"""
a, fc_cache = affine_forward(x, w, b)
out, relu_cache = relu_forward(a)
cache = (fc_cache, relu_cache)
return out, cache
def softmax_loss(x, y):
"""
Computes the loss and gradient for softmax classification. Inputs:
- x: Input data, of shape (N, C) where x[i, j] is the score for the jth class
for the ith input.
- y: Vector of labels, of shape (N,) where y[i] is the label for x[i] and
0 <= y[i] < C
Returns a tuple of:
- loss: Scalar giving the loss
- dx: Gradient of the loss with respect to x
"""
probs = np.exp(x - np.max(x, axis=1, keepdims=True))
probs /= np.sum(probs, axis=1, keepdims=True)
N = x.shape[0]
loss = -np.sum(np.log(probs[np.arange(N), y])) / N
dx = probs.copy()
dx[np.arange(N), y] -= 1
dx /= N
return loss, dx
def affine_relu_backward(dout, cache):
"""
Backward pass for the affine-relu convenience layer
"""
fc_cache, relu_cache = cache
da = relu_backward(dout, relu_cache)
dx, dw, db = affine_backward(da, fc_cache)
return dx, dw, db
layers.py
import numpy as np
def affine_forward(x, w, b):
"""
Computes the forward pass for an affine (fully-connected) layer.
The input x has shape (N, d_1, ..., d_k) and contains a minibatch of N
examples, where each example x[i] has shape (d_1, ..., d_k). We will
reshape each input into a vector of dimension D = d_1 * ... * d_k, and
then transform it to an output vector of dimension M.
Inputs:
- x: A numpy array containing input data, of shape (N, d_1, ..., d_k)
- w: A numpy array of weights, of shape (D, M)
- b: A numpy array of biases, of shape (M,)
Returns a tuple of:
- out: output, of shape (N, M)
- cache: (x, w, b)
"""
out = None
# Reshape x into rows
N = x.shape[0]
x_row = x.reshape(N, -1) # (N,D)
out = np.dot(x_row, w) + b # (N,M)
cache = (x, w, b)
return out, cache
def relu_forward(x):
"""
Computes the forward pass for a layer of rectified linear units (ReLUs).
Input:
- x: Inputs, of any shape
Returns a tuple of:
- out: Output, of the same shape as x
- cache: x
"""
out = None
out = ReLU(x)
cache = x
return out, cache
def ReLU(x):
"""ReLU non-linearity."""
return np.maximum(0, x)
def affine_backward(dout, cache):
"""
Computes the backward pass for an affine layer.
Inputs:
- dout: Upstream derivative, of shape (N, M)
- cache: Tuple of:
- x: Input data, of shape (N, d_1, ... d_k)
- w: Weights, of shape (D, M)
Returns a tuple of:
- dx: Gradient with respect to x, of shape (N, d1, ..., d_k)
- dw: Gradient with respect to w, of shape (D, M)
- db: Gradient with respect to b, of shape (M,)
"""
x, w, b = cache
dx, dw, db = None, None, None
dx = np.dot(dout, w.T) # (N,D)
dx = np.reshape(dx, x.shape) # (N,d1,...,d_k)
x_row = x.reshape(x.shape[0], -1) # (N,D)
dw = np.dot(x_row.T, dout) # (D,M)
db = np.sum(dout, axis=0, keepdims=True) # (1,M)
return dx, dw, db
def relu_backward(dout, cache):
"""
Computes the backward pass for a layer of rectified linear units (ReLUs).
Input:
- dout: Upstream derivatives, of any shape
- cache: Input x, of same shape as dout
Returns:
- dx: Gradient with respect to x
"""
dx, x = None, cache
dx = dout
dx[x <= 0] = 0
return dx