example/memcost/inception_memcost.py

# pylint: skip-file
import sys
sys.path.append('../../python/')
import mxnet as mx
import logging

def ConvFactory(data, num_filter, kernel, stride=(1,1), pad=(0, 0), name=None, suffix=''):
    conv = mx.symbol.Convolution(data=data, num_filter=num_filter, kernel=kernel, stride=stride, pad=pad, name='conv_%s%s' %(name, suffix))
    bn = mx.symbol.BatchNorm(data=conv, name='bn_%s%s' %(name, suffix))
    act = mx.symbol.Activation(data=bn, act_type='relu', name='relu_%s%s' %(name, suffix))
    return act

def InceptionFactoryA(data, num_1x1, num_3x3red, num_3x3, num_d3x3red, num_d3x3, pool, proj, name):
    # 1x1
    c1x1 = ConvFactory(data=data, num_filter=num_1x1, kernel=(1, 1), name=('%s_1x1' % name))
    # 3x3 reduce + 3x3
    c3x3r = ConvFactory(data=data, num_filter=num_3x3red, kernel=(1, 1), name=('%s_3x3' % name), suffix='_reduce')
    c3x3 = ConvFactory(data=c3x3r, num_filter=num_3x3, kernel=(3, 3), pad=(1, 1), name=('%s_3x3' % name))
    # double 3x3 reduce + double 3x3
    cd3x3r = ConvFactory(data=data, num_filter=num_d3x3red, kernel=(1, 1), name=('%s_double_3x3' % name), suffix='_reduce')
    cd3x3 = ConvFactory(data=cd3x3r, num_filter=num_d3x3, kernel=(3, 3), pad=(1, 1), name=('%s_double_3x3_0' % name))
    cd3x3 = ConvFactory(data=cd3x3, num_filter=num_d3x3, kernel=(3, 3), pad=(1, 1), name=('%s_double_3x3_1' % name))
    # pool + proj
    pooling = mx.symbol.Pooling(data=data, kernel=(3, 3), stride=(1, 1), pad=(1, 1), pool_type=pool, name=('%s_pool_%s_pool' % (pool, name)))
    cproj = ConvFactory(data=pooling, num_filter=proj, kernel=(1, 1), name=('%s_proj' %  name))
    # concat
    concat = mx.symbol.Concat(*[c1x1, c3x3, cd3x3, cproj], name='ch_concat_%s_chconcat' % name)
    return concat

def InceptionFactoryB(data, num_3x3red, num_3x3, num_d3x3red, num_d3x3, name):
    # 3x3 reduce + 3x3
    c3x3r = ConvFactory(data=data, num_filter=num_3x3red, kernel=(1, 1), name=('%s_3x3' % name), suffix='_reduce')
    c3x3 = ConvFactory(data=c3x3r, num_filter=num_3x3, kernel=(3, 3), pad=(1, 1), stride=(2, 2), name=('%s_3x3' % name))
    # double 3x3 reduce + double 3x3
    cd3x3r = ConvFactory(data=data, num_filter=num_d3x3red, kernel=(1, 1),  name=('%s_double_3x3' % name), suffix='_reduce')
    cd3x3 = ConvFactory(data=cd3x3r, num_filter=num_d3x3, kernel=(3, 3), pad=(1, 1), stride=(1, 1), name=('%s_double_3x3_0' % name))
    cd3x3 = ConvFactory(data=cd3x3, num_filter=num_d3x3, kernel=(3, 3), pad=(1, 1), stride=(2, 2), name=('%s_double_3x3_1' % name))
    # pool + proj
    pooling = mx.symbol.Pooling(data=data, kernel=(3, 3), stride=(2, 2), pad=(1, 1), pool_type="max", name=('max_pool_%s_pool' % name))
    # concat
    concat = mx.symbol.Concat(*[c3x3, cd3x3, pooling], name='ch_concat_%s_chconcat' % name)
    return concat

def inception(nhidden, grad_scale):
    # data
    data = mx.symbol.Variable(name="data")
    # stage 1
    conv1 = ConvFactory(data=data, num_filter=64, kernel=(7, 7), stride=(2, 2), pad=(3, 3), name='conv1')
    pool1 = mx.symbol.Pooling(data=conv1, kernel=(3, 3), stride=(2, 2), name='pool1', pool_type='max')
    # stage 2
    conv2red = ConvFactory(data=pool1, num_filter=64, kernel=(1, 1), stride=(1, 1), name='conv2red')
    conv2 = ConvFactory(data=conv2red, num_filter=192, kernel=(3, 3), stride=(1, 1), pad=(1, 1), name='conv2')
    pool2 = mx.symbol.Pooling(data=conv2, kernel=(3, 3), stride=(2, 2), name='pool2', pool_type='max')
    # stage 2
    in3a = InceptionFactoryA(pool2, 64, 64, 64, 64, 96, "avg", 32, '3a')
    in3b = InceptionFactoryA(in3a, 64, 64, 96, 64, 96, "avg", 64, '3b')
    in3c = InceptionFactoryB(in3b, 128, 160, 64, 96, '3c')
    # stage 3
    in4a = InceptionFactoryA(in3c, 224, 64, 96, 96, 128, "avg", 128, '4a')
    in4b = InceptionFactoryA(in4a, 192, 96, 128, 96, 128, "avg", 128, '4b')
    in4c = InceptionFactoryA(in4b, 160, 128, 160, 128, 160, "avg", 128, '4c')
    in4d = InceptionFactoryA(in4c, 96, 128, 192, 160, 192, "avg", 128, '4d')
    in4e = InceptionFactoryB(in4d, 128, 192, 192, 256, '4e')
    # stage 4
    in5a = InceptionFactoryA(in4e, 352, 192, 320, 160, 224, "avg", 128, '5a')
    in5b = InceptionFactoryA(in5a, 352, 192, 320, 192, 224, "max", 128, '5b')
    # global avg pooling
    avg = mx.symbol.Pooling(data=in5b, kernel=(7, 7), stride=(1, 1), name="global_pool", pool_type='avg')
    # linear classifier
    flatten = mx.symbol.Flatten(data=avg, name='flatten')
    fc1 = mx.symbol.FullyConnected(data=flatten, num_hidden=nhidden, name='fc1')
    softmax = mx.symbol.SoftmaxOutput(data=fc1, name='softmax')
    return softmax



softmax = inception(1000, 1.0)
batch_size = 32
softmax = inception(1000, 1.0)

if len(sys.argv) == 2:
    grad_req = sys.argv[1]
else:
    grad_req = 'write'

texec = softmax.simple_bind(ctx=mx.cpu(),
                            data=(batch_size, 3, 224, 224),
                            grad_req=grad_req)
# We extract the memory cost from the execution plan
print(texec.debug_str().split('\n')[-3])