Source code for mxnet.gluon.model_zoo.vision.mobilenet

# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.

# coding: utf-8
# pylint: disable= arguments-differ
"""MobileNet, implemented in Gluon."""
__all__ = ['MobileNet', 'mobilenet1_0', 'mobilenet0_75', 'mobilenet0_5', 'mobilenet0_25',
           'get_mobilenet']

from ....context import cpu
from ...block import HybridBlock
from ... import nn

# Helpers
def _add_conv(out, channels=1, kernel=1, stride=1, pad=0, num_group=1):
    out.add(nn.Conv2D(channels, kernel, stride, pad, groups=num_group, use_bias=False))
    out.add(nn.BatchNorm(scale=False))
    out.add(nn.Activation('relu'))

def _add_conv_dw(out, dw_channels, channels, stride):
    _add_conv(out, channels=dw_channels, kernel=3, stride=stride, pad=1, num_group=dw_channels)
    _add_conv(out, channels=channels)


# Net
[docs]class MobileNet(HybridBlock): r"""MobileNet model from the `"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications" `_ paper. Parameters ---------- multiplier : float, default 1.0 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. classes : int, default 1000 Number of classes for the output layer. """ def __init__(self, multiplier=1.0, classes=1000, **kwargs): super(MobileNet, self).__init__(**kwargs) with self.name_scope(): self.features = nn.HybridSequential(prefix='') with self.features.name_scope(): _add_conv(self.features, channels=int(32*multiplier), kernel=3, pad=1, stride=2) dw_channels = [int(x*multiplier) for x in [32, 64]+[128]*2+[256]*2+[512]*6+[1024]] channels = [int(x*multiplier) for x in [64]+[128]*2+[256]*2+[512]*6+[1024]*2] strides = [1, 2] * 3 + [1] * 5 + [2, 1] for dwc, c, s in zip(dw_channels, channels, strides): _add_conv_dw(self.features, dw_channels=dwc, channels=c, stride=s) self.features.add(nn.GlobalAvgPool2D()) self.features.add(nn.Flatten()) self.output = nn.Dense(classes) def hybrid_forward(self, F, x): x = self.features(x) x = self.output(x) return x
# Constructor
[docs]def get_mobilenet(multiplier, pretrained=False, ctx=cpu(), root='~/.mxnet/models', **kwargs): r"""MobileNet model from the `"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications" `_ 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. pretrained : bool, default False Whether to load the pretrained weights for model. ctx : Context, default CPU The context in which to load the pretrained weights. root : str, default '~/.mxnet/models' Location for keeping the model parameters. """ net = MobileNet(multiplier, **kwargs) if pretrained: from ..model_store import get_model_file version_suffix = '{0:.2f}'.format(multiplier) if version_suffix in ('1.00', '0.50'): version_suffix = version_suffix[:-1] net.load_params(get_model_file('mobilenet%s'%version_suffix, root=root), ctx=ctx) return net
[docs]def mobilenet1_0(**kwargs): r"""MobileNet model from the `"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications" `_ paper, with width multiplier 1.0. Parameters ---------- pretrained : bool, default False Whether to load the pretrained weights for model. ctx : Context, default CPU The context in which to load the pretrained weights. """ return get_mobilenet(1.0, **kwargs)
[docs]def mobilenet0_75(**kwargs): r"""MobileNet model from the `"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications" `_ paper, with width multiplier 0.75. Parameters ---------- pretrained : bool, default False Whether to load the pretrained weights for model. ctx : Context, default CPU The context in which to load the pretrained weights. """ return get_mobilenet(0.75, **kwargs)
[docs]def mobilenet0_5(**kwargs): r"""MobileNet model from the `"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications" `_ paper, with width multiplier 0.5. Parameters ---------- pretrained : bool, default False Whether to load the pretrained weights for model. ctx : Context, default CPU The context in which to load the pretrained weights. """ return get_mobilenet(0.5, **kwargs)
[docs]def mobilenet0_25(**kwargs): r"""MobileNet model from the `"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications" `_ paper, with width multiplier 0.25. Parameters ---------- pretrained : bool, default False Whether to load the pretrained weights for model. ctx : Context, default CPU The context in which to load the pretrained weights. """ return get_mobilenet(0.25, **kwargs)