#!/usr/bin/env python2# -*- coding: utf-8 -*-"""Created on Fri Aug 10 16:13:29 2018@author: myhaspl"""from mxnet import ndfrom mxnet.gluon import nnnet = nn.Sequential()# Add a sequence of layers.net.add(# Similar to Dense, it is not necessary to specify the# input channels by the argument `in_channels`, which will be # automatically inferred in the first forward pass. Also,# we apply a relu activation on the output.## In addition, we can use a tuple to specify a# non-square kernel size, such as `kernel_size=(2,4)nn.Conv2D(channels=6, kernel_size=5, activation=‘relu‘),# One can also use a tuple to specify non-symmetric# pool and stride sizesnn.MaxPool2D(pool_size=2, strides=2),nn.Conv2D(channels=16, kernel_size=3, activation=‘relu‘), nn.MaxPool2D(pool_size=2, strides=2),# flatten the 4-D input into 2-D with shape# `(x.shape[0], x.size/x.shape[0])` so that it can be used# by the following dense layersnn.Flatten(),nn.Dense(120, activation="relu"),nn.Dense(84, activation="relu"),nn.Dense(10))print netnet.initialize()x = nd.random.uniform(shape=(4,1,28,28))y = net(x)print y.shapeprint net[0].weight.data().shapeprint net[7].weight.data().shapeSequential(? (0): Conv2D(None -> 6, kernel_size=(5, 5), stride=(1, 1))? (1): MaxPool2D(size=(2, 2), stride=(2, 2), padding=(0, 0), ceil_mode=False)? (2): Conv2D(None -> 16, kernel_size=(3, 3), stride=(1, 1))? (3): MaxPool2D(size=(2, 2), stride=(2, 2), padding=(0, 0), ceil_mode=False)? (4): Flatten? (5): Dense(None -> 120, Activation(relu))? (6): Dense(None -> 84, Activation(relu))? (7): Dense(None -> 10, linear))(4L, 10L)
(6L, 1L, 5L, 5L)
(10L, 84L)
mxnet-Sequential
原文地址：http://blog.51cto.com/13959448/2316507