"Mxnet"의 두 판 사이의 차이
ph
잔글 (→etc) |
잔글 (→etc) |
||
| 9번째 줄: | 9번째 줄: | ||
==etc== | ==etc== | ||
* batch normalization example | * batch normalization example | ||
| − | <pre>def ConvFactory(data, num_filter, kernel, stride=(1,1), pad=(0, 0),name=None, suffix=''): | + | <pre>def ConvFactory(data, num_filter, kernel, |
| − | conv = mx.sym.Convolution(data=data, num_filter=num_filter, kernel=kernel, | + | stride=(1,1), pad=(0, 0),name=None, suffix=''): |
| − | stride=stride, pad=pad, name='conv_%s%s' %(name, suffix)) | + | conv = mx.sym.Convolution(data=data, |
| + | num_filter=num_filter, | ||
| + | kernel=kernel, | ||
| + | stride=stride, | ||
| + | pad=pad, | ||
| + | name='conv_%s%s' %(name, suffix)) | ||
bn = mx.sym.BatchNorm(data=conv, name='bn_%s%s' %(name, suffix)) | bn = mx.sym.BatchNorm(data=conv, name='bn_%s%s' %(name, suffix)) | ||
act = mx.sym.Activation(data=bn, act_type='relu', name='relu_%s%s' | act = mx.sym.Activation(data=bn, act_type='relu', name='relu_%s%s' | ||
2017년 7월 4일 (화) 19:05 판
뭘 이렇게들 만들어 대는지. tf가 맘에 안들기는 하지만.
etc
- batch normalization example
def ConvFactory(data, num_filter, kernel,
stride=(1,1), pad=(0, 0),name=None, suffix=''):
conv = mx.sym.Convolution(data=data,
num_filter=num_filter,
kernel=kernel,
stride=stride,
pad=pad,
name='conv_%s%s' %(name, suffix))
bn = mx.sym.BatchNorm(data=conv, name='bn_%s%s' %(name, suffix))
act = mx.sym.Activation(data=bn, act_type='relu', name='relu_%s%s'
%(name, suffix))
return act
- feature extraction Predict with pre-trained models