These are chat archives for dmlc/mxnet

16th
Nov 2015
Zhang Ming
@starimpact
Nov 16 2015 00:10
can anyone help me to check #554 ?
Zhang Ming
@starimpact
Nov 16 2015 01:39
I don't know how to make a layer be a loss function.I know how to do with python, in which I can set init(False)
help me.....
Zhang Ming
@starimpact
Nov 16 2015 08:44
hello guys
    tdata_out = F<mshadow_op::log>(tdata_in + MIN_NUM) * tlabel +
                (1.0f - tlabel) * F<mshadow_op::log>(1.0f - tdata_in + MIN_NUM);
    tdata_out = tdata_out * tmarklabel * -1;
cause warning:
./mshadow/mshadow/tensor.h: In function ‘void mshadow::MapExp(mshadow::TRValue<R, mshadow::gpu, dim, DType>*, const mshadow::expr::Exp<E, DType, etype>&) [with Saver = mshadow::sv::saveto; R = mshadow::Tensor<mshadow::gpu, 2, float>; int dim = 2; DType = float; E = mshadow::expr::BinaryMapExp<mshadow::op::minus, mshadow::expr::BinaryMapExp<mshadow::op::div, mshadow::Tensor<mshadow::gpu, 2, float>, mshadow::expr::BinaryMapExp<mshadow::op::plus, mshadow::Tensor<mshadow::gpu, 2, float>, mshadow::expr::ScalarExp<float>, float, 1>, float, 1>, mshadow::expr::BinaryMapExp<mshadow::op::div, mshadow::expr::BinaryMapExp<mshadow::op::minus, mshadow::expr::ScalarExp<float>, mshadow::Tensor<mshadow::gpu, 2, float>, float, 1>, mshadow::expr::BinaryMapExp<mshadow::op::plus, mshadow::expr::BinaryMapExp<mshadow::op::minus, mshadow::expr::ScalarExp<float>, mshadow::Tensor<mshadow::gpu, 2, float>, float, 1>, mshadow::expr::ScalarExp<float>, float, 1>, float, 1>, float, 1>; int etype = 1]’:
./mshadow/mshadow/tensor.h:67:1: warning: ‘shape2.mshadow::Shape<2>::shape_[1u]’ may be used uninitialized in this function [-Wmaybe-uninitialized]
       this->shape_[i] = s[i];
 ^
./mshadow/mshadow/././expr_engine-inl.h:361:13: note: ‘shape2’ was declared here
     Shape<dim> shape2 = ShapeCheck<dim, TB>::Check(t.rhs_);
             ^
what's the problem with the expression , how can I remove the warning?
Zhang Ming
@starimpact
Nov 16 2015 21:37
help me on issue #594
i have finished the cpp verion
but can not work on gpu
cpu is ok
@tqchen @winstywang @vchuravy
Zhang Ming
@starimpact
Nov 16 2015 22:14
@piiswrong
😭
😭😪😥😰😅😓😢😂