mxnet相关

data = mx.sym.Variable(name='data')

data= mx.sym.BatchNorm(data=data, fix_gamma=True, eps=2e-5, momentum=bn_mom, name='bn_data')

body = mx.sym.Convolution(data=data, num_filter=filter_list[0], kernel=(7, 7), stride=(2,2), pad=(3, 3), no_bias=True, name="conv0", workspace=workspace)

bn1 = mx.sym.BatchNorm(data=body, fix_gamma=False, eps=2e-5, momentum=bn_mom, name='bn1')

relu1 = mx.sym.Activation(data=bn1, act_type='relu', name='relu1')

pool1 = mx.symbol.Pooling(data=relu1, global_pool=True, kernel=(7, 7), pool_type='avg', name='pool1')

flat = mx.symbol.Flatten(data=pool1)

fc1 = mx.symbol.FullyConnected(data=flat, num_hidden=num_class, name='fc1')

out=mx.symbol.SoftmaxOutput(data=fc1, name='softmax')

在mxnet中Symbol包含两种，

                          1.一种叫variable，代表变量

                         2.一种叫op代表操作节点。例子中的mx.sym.Variable定义的就是variable类型的Symbol。其他行定义都是op型的Symbol

op指的是最小的计算单元，caffe里叫layer