深度网络及经典网络简介

导语
加深网络
- 一个更深的CNN
- 提高识别精度
- - Data Augmentation
- 层的加深
经典网络
- VGG
- GoogLeNet
- ResNet
高速学习
- 迁移学习
- GPU
- 分布式学习
- 计算位缩减
强化学习
总结
参考文献

导语

深度学习简单来说，就是加深了层数的神经网络，前面已经提到，网络的层数越深，它学习到的特征就越抽象，越高级，这也是深度网络能够胜任很多工作的原因。

加深网络

书上在本章将前面的各种技术结合起来，构建了一个复杂的深层网络，以MNIST数据集的手写识别为数据集进行训练和验证。

一个更深的CNN

书上给出了一个构造好的CNN，如下图，可以发现它比先前构造的任何网络都更深，并且使用了Dropout，选取的卷积核都是3×3，激活函数采用ReLU，使用Adam最优化，以He初始值为权重初始值。

在这里插入图片描述
书上给出的代码如下：

class DeepConvNet: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):#输入维度，卷积层数量，卷积层规模，填充，步长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):#预测for layer in self.layers:if isinstance(layer, Dropout):x = layer.forward(x, train_flg)else:x = layer.forward(x)return xdef loss(self, x, t):#计算损失y = self.predict(x, train_flg=True)return self.last_layer.forward(y, t)def accuracy(self, x, t, batch_size=100):#返回准确度if t.ndim != 1 : t = np.argmax(t, axis=1)acc = 0.0for 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):# forwardself.loss(x, t)# backwarddout = 1dout = 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].dWgrads['b' + str(i+1)] = self.layers[layer_idx].dbreturn grads