resnet.py

# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed 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.

from __future__ import print_function

import paddle.fluid as fluid

__all__ = ['resnet_cifar10']


def conv_bn_layer(input,
                  ch_out,
                  filter_size,
                  stride,
                  padding,
                  act='relu',
                  bias_attr=False):
    tmp = fluid.layers.conv2d(
        input=input,
        filter_size=filter_size,
        num_filters=ch_out,
        stride=stride,
        padding=padding,
        act=None,
        bias_attr=bias_attr)
    return fluid.layers.batch_norm(input=tmp, act=act)


def shortcut(input, ch_in, ch_out, stride):
    if ch_in != ch_out:
        return conv_bn_layer(input, ch_out, 1, stride, 0, None)
    else:
        return input


def basicblock(input, ch_in, ch_out, stride):
    tmp = conv_bn_layer(input, ch_out, 3, stride, 1)
    tmp = conv_bn_layer(tmp, ch_out, 3, 1, 1, act=None, bias_attr=True)
    short = shortcut(input, ch_in, ch_out, stride)
    return fluid.layers.elementwise_add(x=tmp, y=short, act='relu')


def layer_warp(block_func, input, ch_in, ch_out, count, stride):
    tmp = block_func(input, ch_in, ch_out, stride)
    for i in range(1, count):
        tmp = block_func(tmp, ch_out, ch_out, 1)
    return tmp


def resnet_cifar10(ipt, depth=32):
    # depth should be one of 20, 32, 44, 56, 110, 1202
    assert (depth - 2) % 6 == 0
    n = (depth - 2) // 6
    nStages = {16, 64, 128}
    conv1 = conv_bn_layer(ipt, ch_out=16, filter_size=3, stride=1, padding=1)
    res1 = layer_warp(basicblock, conv1, 16, 16, n, 1)
    res2 = layer_warp(basicblock, res1, 16, 32, n, 2)
    res3 = layer_warp(basicblock, res2, 32, 64, n, 2)
    pool = fluid.layers.pool2d(
        input=res3, pool_size=8, pool_type='avg', pool_stride=1)
    predict = fluid.layers.fc(input=pool, size=10, act='softmax')
    return predict