python/mxnet/gluon/model_zoo/vision/vgg.py

# 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
"""VGG, implemented in Gluon."""
__all__ = ['VGG',
           'vgg11', 'vgg13', 'vgg16', 'vgg19',
           'vgg11_bn', 'vgg13_bn', 'vgg16_bn', 'vgg19_bn',
           'get_vgg']

import os

from ....device import cpu
from ....initializer import Xavier
from ...block import HybridBlock
from ... import nn
from .... import base
from ....util import use_np, wrap_ctx_to_device_func


@use_np
class VGG(HybridBlock):
    r"""VGG model from the `"Very Deep Convolutional Networks for Large-Scale Image Recognition"
    <https://arxiv.org/abs/1409.1556>`_ paper.

    Parameters
    ----------
    layers : list of int
        Numbers of layers in each feature block.
    filters : list of int
        Numbers of filters in each feature block. List length should match the layers.
    classes : int, default 1000
        Number of classification classes.
    batch_norm : bool, default False
        Use batch normalization.
    """
    def __init__(self, layers, filters, classes=1000, batch_norm=False, **kwargs):
        super(VGG, self).__init__(**kwargs)
        assert len(layers) == len(filters)
        self.features = self._make_features(layers, filters, batch_norm)
        self.features.add(nn.Dense(4096, activation='relu',
                                   weight_initializer='normal',
                                   bias_initializer='zeros'))
        self.features.add(nn.Dropout(rate=0.5))
        self.features.add(nn.Dense(4096, activation='relu',
                                   weight_initializer='normal',
                                   bias_initializer='zeros'))
        self.features.add(nn.Dropout(rate=0.5))
        self.output = nn.Dense(classes,
                               weight_initializer='normal',
                               bias_initializer='zeros')

    def _make_features(self, layers, filters, batch_norm):
        featurizer = nn.HybridSequential()
        for i, num in enumerate(layers):
            for _ in range(num):
                featurizer.add(nn.Conv2D(filters[i], kernel_size=3, padding=1,
                                         weight_initializer=Xavier(rnd_type='gaussian',
                                                                   factor_type='out',
                                                                   magnitude=2),
                                         bias_initializer='zeros'))
                if batch_norm:
                    featurizer.add(nn.BatchNorm())
                featurizer.add(nn.Activation('relu'))
            featurizer.add(nn.MaxPool2D(strides=2))
        return featurizer

    def forward(self, x):
        x = self.features(x)
        x = self.output(x)
        return x


# Specification
vgg_spec = {11: ([1, 1, 2, 2, 2], [64, 128, 256, 512, 512]),
            13: ([2, 2, 2, 2, 2], [64, 128, 256, 512, 512]),
            16: ([2, 2, 3, 3, 3], [64, 128, 256, 512, 512]),
            19: ([2, 2, 4, 4, 4], [64, 128, 256, 512, 512])}


# Constructors
@wrap_ctx_to_device_func
def get_vgg(num_layers, pretrained=False, device=cpu(),
            root=os.path.join(base.data_dir(), 'models'), **kwargs):
    r"""VGG model from the `"Very Deep Convolutional Networks for Large-Scale Image Recognition"
    <https://arxiv.org/abs/1409.1556>`_ paper.

    Parameters
    ----------
    num_layers : int
        Number of layers for the variant of densenet. Options are 11, 13, 16, 19.
    pretrained : bool, default False
        Whether to load the pretrained weights for model.
    device : Device, default CPU
        The device in which to load the pretrained weights.
    root : str, default $MXNET_HOME/models
        Location for keeping the model parameters.
    """
    layers, filters = vgg_spec[num_layers]
    net = VGG(layers, filters, **kwargs)
    if pretrained:
        from ..model_store import get_model_file
        batch_norm_suffix = '_bn' if kwargs.get('batch_norm') else ''
        net.load_parameters(get_model_file(f'vgg{num_layers}{batch_norm_suffix}',
                                           root=root), device=device)
    return net

@wrap_ctx_to_device_func
def vgg11(**kwargs):
    r"""VGG-11 model from the `"Very Deep Convolutional Networks for Large-Scale Image Recognition"
    <https://arxiv.org/abs/1409.1556>`_ paper.

    Parameters
    ----------
    pretrained : bool, default False
        Whether to load the pretrained weights for model.
    device : Device, default CPU
        The device in which to load the pretrained weights.
    root : str, default '$MXNET_HOME/models'
        Location for keeping the model parameters.
    """
    return get_vgg(11, **kwargs)

@wrap_ctx_to_device_func
def vgg13(**kwargs):
    r"""VGG-13 model from the `"Very Deep Convolutional Networks for Large-Scale Image Recognition"
    <https://arxiv.org/abs/1409.1556>`_ paper.

    Parameters
    ----------
    pretrained : bool, default False
        Whether to load the pretrained weights for model.
    device : Device, default CPU
        The device in which to load the pretrained weights.
    root : str, default '$MXNET_HOME/models'
        Location for keeping the model parameters.
    """
    return get_vgg(13, **kwargs)

@wrap_ctx_to_device_func
def vgg16(**kwargs):
    r"""VGG-16 model from the `"Very Deep Convolutional Networks for Large-Scale Image Recognition"
    <https://arxiv.org/abs/1409.1556>`_ paper.

    Parameters
    ----------
    pretrained : bool, default False
        Whether to load the pretrained weights for model.
    device : Device, default CPU
        The device in which to load the pretrained weights.
    root : str, default '$MXNET_HOME/models'
        Location for keeping the model parameters.
    """
    return get_vgg(16, **kwargs)

@wrap_ctx_to_device_func
def vgg19(**kwargs):
    r"""VGG-19 model from the `"Very Deep Convolutional Networks for Large-Scale Image Recognition"
    <https://arxiv.org/abs/1409.1556>`_ paper.

    Parameters
    ----------
    pretrained : bool, default False
        Whether to load the pretrained weights for model.
    device : Device, default CPU
        The device in which to load the pretrained weights.
    root : str, default '$MXNET_HOME/models'
        Location for keeping the model parameters.
    """
    return get_vgg(19, **kwargs)

@wrap_ctx_to_device_func
def vgg11_bn(**kwargs):
    r"""VGG-11 model with batch normalization from the
    `"Very Deep Convolutional Networks for Large-Scale Image Recognition"
    <https://arxiv.org/abs/1409.1556>`_ paper.

    Parameters
    ----------
    pretrained : bool, default False
        Whether to load the pretrained weights for model.
    device : Device, default CPU
        The device in which to load the pretrained weights.
    root : str, default '$MXNET_HOME/models'
        Location for keeping the model parameters.
    """
    kwargs['batch_norm'] = True
    return get_vgg(11, **kwargs)

@wrap_ctx_to_device_func
def vgg13_bn(**kwargs):
    r"""VGG-13 model with batch normalization from the
    `"Very Deep Convolutional Networks for Large-Scale Image Recognition"
    <https://arxiv.org/abs/1409.1556>`_ paper.

    Parameters
    ----------
    pretrained : bool, default False
        Whether to load the pretrained weights for model.
    device : Device, default CPU
        The device in which to load the pretrained weights.
    root : str, default '$MXNET_HOME/models'
        Location for keeping the model parameters.
    """
    kwargs['batch_norm'] = True
    return get_vgg(13, **kwargs)

@wrap_ctx_to_device_func
def vgg16_bn(**kwargs):
    r"""VGG-16 model with batch normalization from the
    `"Very Deep Convolutional Networks for Large-Scale Image Recognition"
    <https://arxiv.org/abs/1409.1556>`_ paper.

    Parameters
    ----------
    pretrained : bool, default False
        Whether to load the pretrained weights for model.
    device : Device, default CPU
        The device in which to load the pretrained weights.
    root : str, default '$MXNET_HOME/models'
        Location for keeping the model parameters.
    """
    kwargs['batch_norm'] = True
    return get_vgg(16, **kwargs)

@wrap_ctx_to_device_func
def vgg19_bn(**kwargs):
    r"""VGG-19 model with batch normalization from the
    `"Very Deep Convolutional Networks for Large-Scale Image Recognition"
    <https://arxiv.org/abs/1409.1556>`_ paper.

    Parameters
    ----------
    pretrained : bool, default False
        Whether to load the pretrained weights for model.
    device : Device, default CPU
        The device in which to load the pretrained weights.
    root : str, default '$MXNET_HOME/models'
        Location for keeping the model parameters.
    """
    kwargs['batch_norm'] = True
    return get_vgg(19, **kwargs)