mxnet 基本model 结构输入输出，名字形状，会默认在名字后面加，_out,_weight,_bias

https://blog.csdn.net/wangjuncode/article/details/94209799

# 对于如下的普通网络：
import mxnet as mx
import mxnet.ndarray as nd
 
def mxnet_symbol_demo():
    data = mx.sym.Variable('data') 
    # layer1 
    conv1 = mx.sym.Convolution(data=data, kernel=(5,5), num_filter=32,name="conv1")
    relu1 = mx.sym.Activation(data=conv1,act_type="relu",name="relu1") 
    pool1 = mx.sym.Pooling(data=relu1,pool_type="max",kernel=(2,2),stride=(2,2),name="pool1") 
    # layer2 
    conv2 = mx.sym.Convolution(data=pool1, kernel=(3,3), num_filter=64,name="conv2") 
    relu2 = mx.sym.Activation(data=conv2,act_type="relu",name="relu2") 
    pool2 = mx.sym.Pooling(data=relu2,pool_type="max",kernel=(2,2),stride=(2,2),name="pool2") 
    # layer3 
    fc1 = mx.symbol.FullyConnected(data=mx.sym.flatten(pool2), num_hidden=256,name="fc1") 
    relu3 = mx.sym.Activation(data=fc1, act_type="relu",name="relu3") 
    # layer4 
    fc2 = mx.symbol.FullyConnected(data=relu3, num_hidden=10,name="fc2")
    out = mx.sym.SoftmaxOutput(data=fc2, label=mx.sym.Variable("label"),name='softmax')
 
    return  out

if __name__=="__main__":
    sym=mxnet_symbol_demo()
    out_list=sym.get_internals().list_outputs()
    print(out_list)
 
    # result:
    # ['data', 'conv1_weight', 'conv1_bias', 'conv1_output', 
    # 'relu1_output', 'pool1_output', 'conv2_weight', 'conv2_bias', 
    # 'conv2_output', 'relu2_output', 'pool2_output', 'flatten0_output', 
    # 'fc1_weight', 'fc1_bias', 'fc1_output', 'relu3_output', 'fc2_weight', 
    # 'fc2_bias', 'fc2_output', 'label', 'softmax_output']

————————————————
版权声明：本文为CSDN博主「SeekingWJ」的原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/wangjuncode/article/details/94209799