import matplotlib
matplotlib.use('Agg')
import argparse,time,logging
import mxnet as mx
import numpy as np
from mxnet import gluon,nd
from mxnet.gluon import nn
from mxnet.gluon.data.vision import transforms
from gluoncv.data import imagenet
from gluoncv.utils import makedirs, TrainingHistory
import os
from mxnet.context import cpu
from mxnet.gluon.block import HybridBlock
from mxnet.gluon.contrib.nn import HybridConcurrent
import multiprocessing
import logging
logging.basicConfig(level=logging.INFO)
##This block contains definition for Mobilenet v2
# Helpers
class RELU6(nn.HybridBlock):
"""Relu6 used in MobileNetV2."""
def __init__(self, **kwargs):
super(RELU6, self).__init__(**kwargs)
def hybrid_forward(self, F, x):
return F.clip(x, 0, 6, name="relu6")
def _add_conv(out, channels=1, kernel=1, stride=1, pad=0,
num_group=1, active=True, relu6=False):
out.add(nn.Conv2D(channels, kernel, stride, pad, groups=num_group, use_bias=False))
out.add(nn.BatchNorm(scale=True))
if active:
out.add(RELU6() if relu6 else nn.Activation('relu'))
def _add_conv_dw(out, dw_channels, channels, stride, relu6=False):
_add_conv(out, channels=dw_channels, kernel=3, stride=stride,
pad=1, num_group=dw_channels, relu6=relu6)
_add_conv(out, channels=channels, relu6=relu6)
class LinearBottleneck(nn.HybridBlock):
r"""LinearBottleneck used in MobileNetV2 model from the
`"Inverted Residuals and Linear Bottlenecks:
Mobile Networks for Classification, Detection and Segmentation"
`_ paper.
Parameters
----------
in_channels : int
Number of input channels.
channels : int
Number of output channels.
t : int
Layer expansion ratio.
stride : int
stride
"""
def __init__(self, in_channels, channels, t, stride, **kwargs):
super(LinearBottleneck, self).__init__(**kwargs)
self.use_shortcut = stride == 1 and in_channels == channels
with self.name_scope():
self.out = nn.HybridSequential()
_add_conv(self.out, in_channels * t, relu6=True)
_add_conv(self.out, in_channels * t, kernel=3, stride=stride,
pad=1, num_group=in_channels * t, relu6=True)
_add_conv(self.out, channels, active=False, relu6=True)
def hybrid_forward(self, F, x):
out = self.out(x)
if self.use_shortcut:
out = F.elemwise_add(out, x)
return out
# Net
class MobileNetV2(nn.HybridBlock):
r"""MobileNetV2 model from the
`"Inverted Residuals and Linear Bottlenecks:
Mobile Networks for Classification, Detection and Segmentation"
`_ paper.
Parameters
----------
multiplier : float, default 1.0
The width multiplier for controling the model size. The actual number of channels
is equal to the original channel size multiplied by this multiplier.
classes : int, default 1000
Number of classes for the output layer.
"""
def __init__(self, multiplier=1.0, classes=1000, **kwargs):
super(MobileNetV2, self).__init__(**kwargs)
with self.name_scope():
self.features = nn.HybridSequential(prefix='features_')
with self.features.name_scope():
_add_conv(self.features, int(32 * multiplier), kernel=3,
stride=2, pad=1, relu6=True)
in_channels_group = [int(x * multiplier) for x in [32] + [16] + [24] * 2
+ [32] * 3 + [64] * 4 + [96] * 3 + [160] * 3]
channels_group = [int(x * multiplier) for x in [16] + [24] * 2 + [32] * 3
+ [64] * 4 + [96] * 3 + [160] * 3 + [320]]
ts = [1] + [6] * 16
strides = [1, 2] * 2 + [1, 1, 2] + [1] * 6 + [2] + [1] * 3
for in_c, c, t, s in zip(in_channels_group, channels_group, ts, strides):
self.features.add(LinearBottleneck(in_channels=in_c, channels=c,
t=t, stride=s))
last_channels = int(1280 * multiplier) if multiplier > 1.0 else 1280
_add_conv(self.features, last_channels, relu6=True)
self.features.add(nn.GlobalAvgPool2D())
self.output = nn.HybridSequential(prefix='output_')
with self.output.name_scope():
self.output.add(
nn.Conv2D(classes, 1, use_bias=False, prefix='pred_'),
nn.Flatten()
)
def hybrid_forward(self, F, x):
x = self.features(x)
x = self.output(x)
return x
# Constructor
def get_mobilenet_v2(multiplier, **kwargs):
r"""MobileNetV2 model from the
`"Inverted Residuals and Linear Bottlenecks:
Mobile Networks for Classification, Detection and Segmentation"
`_ paper.
Parameters
----------
multiplier : float
The width multiplier for controling the model size. Only multipliers that are no
less than 0.25 are supported. The actual number of channels is equal to the original
channel size multiplied by this multiplier.
"""
net = MobileNetV2(multiplier, **kwargs)
return net
def mobilenet_v2_1_0(**kwargs):
r"""MobileNetV2 model from the
`"Inverted Residuals and Linear Bottlenecks:
Mobile Networks for Classification, Detection and Segmentation"
`_ paper.
"""
return get_mobilenet_v2(1.0, **kwargs)
def mobilenet_v2_0_5(**kwargs):
r"""MobileNetV2 model from the
`"Inverted Residuals and Linear Bottlenecks:
Mobile Networks for Classification, Detection and Segmentation"
`_ paper.
"""
return get_mobilenet_v2(0.5, **kwargs)
models = {
'mobilenetv2_1.0': mobilenet_v2_1_0,
'mobilenetv2_0.5': mobilenet_v2_0_5
}
kwargs={'classes':1000}
# Retireve gluon model
net = models['mobilenetv2_1.0'](**kwargs)
ctx = mx.cpu(0)
net.hybridize()
net.initialize(mx.init.MSRAPrelu(), ctx=ctx)
# 可视化网络
x = mx.sym.var('data')
sym = net(x)
mx.viz.plot_network(sym,node_attrs={"shape":'oval',"fixedsize":'false'}).view() #pycharm使用必须加view()
