AlexNet是2012年ImageNet比赛的冠军,虽然过去了很长时间,但是作为深度学习中的经典模型,AlexNet不但有助于我们理解其中所使用的很多技巧,而且非常有助于提升我们使用深度学习工具箱的熟练度。尤其是我刚入门深度学习,迫切需要一个能让自己熟悉tensorflow的小练习,于是就有了这个小玩意儿......
先放上我的代码:https://github.com/hjptriplebee/AlexNet_with_tensorflow
如果想运行代码,详细的配置要求都在上面链接的readme文件中了。本文建立在一定的tensorflow基础上,不会对太细的点进行说明。
模型结构
关于模型结构网上的文献很多,我这里不赘述,一会儿都在代码里解释。
有一点需要注意,AlexNet将网络分成了上下两个部分,在论文中两部分结构完全相同,唯一不同的是他们放在不同GPU上训练,因为每一层的feature map之间都是独立的(除了全连接层),所以这相当于是提升训练速度的一种方法。很多AlexNet的复现都将上下两部分合并了,因为他们都是在单个GPU上运行的。虽然我也是在单个GPU上运行,但是我还是很想将最原始的网络结构还原出来,所以我的代码里也是分开的。
模型定义
def maxPoolLayer(x, kHeight, kWidth, strideX, strideY, name, padding = "SAME"): """max-pooling""" return tf.nn.max_pool(x, ksize = [1, kHeight, kWidth, 1], strides = [1, strideX, strideY, 1], padding = padding, name = name) def dropout(x, keepPro, name = None): """dropout""" return tf.nn.dropout(x, keepPro, name) def LRN(x, R, alpha, beta, name = None, bias = 1.0): """LRN""" return tf.nn.local_response_normalization(x, depth_radius = R, alpha = alpha, beta = beta, bias = bias, name = name) def fcLayer(x, inputD, outputD, reluFlag, name): """fully-connect""" with tf.variable_scope(name) as scope: w = tf.get_variable("w", shape = [inputD, outputD], dtype = "float") b = tf.get_variable("b", [outputD], dtype = "float") out = tf.nn.xw_plus_b(x, w, b, name = scope.name) if reluFlag: return tf.nn.relu(out) else: return out def convLayer(x, kHeight, kWidth, strideX, strideY, featureNum, name, padding = "SAME", groups = 1):#group为2时等于AlexNet中分上下两部分 """convlutional""" channel = int(x.get_shape()[-1])#获取channel conv = lambda a, b: tf.nn.conv2d(a, b, strides = [1, strideY, strideX, 1], padding = padding)#定义卷积的匿名函数 with tf.variable_scope(name) as scope: w = tf.get_variable("w", shape = [kHeight, kWidth, channel/groups, featureNum]) b = tf.get_variable("b", shape = [featureNum]) xNew = tf.split(value = x, num_or_size_splits = groups, axis = 3)#划分后的输入和权重 wNew = tf.split(value = w, num_or_size_splits = groups, axis = 3) featureMap = [conv(t1, t2) for t1, t2 in zip(xNew, wNew)] #分别提取feature map mergeFeatureMap = tf.concat(axis = 3, values = featureMap) #feature map整合 # print mergeFeatureMap.shape out = tf.nn.bias_add(mergeFeatureMap, b) return tf.nn.relu(tf.reshape(out, mergeFeatureMap.get_shape().as_list()), name = scope.name) #relu后的结果
新闻热点
疑难解答