mxnet随笔-Sequential

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Fri Aug 10 16:13:29 2018

@author: myhaspl
"""
from mxnet import nd
from mxnet.gluon import nn
net = 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 sizes
nn.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 layers
nn.Flatten(),
nn.Dense(120, activation="relu"),
nn.Dense(84, activation="relu"),
nn.Dense(10))
print net
net.initialize()
x = nd.random.uniform(shape=(4,1,28,28))
y = net(x)
print y.shape
print net[0].weight.data().shape
print net[7].weight.data().shape

Sequential(
  (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)