* add nll_loss op test=develop

* Indent MSELoss example docs

* Point out input tensors should be of same shape

test=develop

* Document `MSELoss` input and return parameters

test=release/2.0-beta,test=document_fix

* update bce docs,test=release/2.0

* update docs, test=release/2.0

* Add `paddle.nn.loss.MSELoss`

test=develop

* Move to `nn/layer/loss.py`

test=develop

* Fix dygraph

test=develop

* Add test

test=develop

* Increase numel in test

test=develop

* Add test for input with different dimensions

test=develop

* add approximation for gelu, test=develop

* add functional conv

* add test and doc for function convs, test=develop

* update ConvTransposeOp's InferShape and error message, test=develop

* add hsigmoid, row_conv in paddle.nn(functional and layer), test=develop

* fix hyperlinks in docstring

* add cross_entropy_loss,test=develop
* fix some commnet,test=develop

* add bce_loss

* fix mistake

* replace paddle_enforce,test=develop

* fix,test=develop

* update,test=develop

* remove duplicate,test=develop

* update,test=develop

* update error,test=develop

* update,test=develop

* fix unittest, test=develop

* update, test=develop

* add instance_norm op for dygraph, test=develop

* add error message, test=develop

* add Conv/ConvTranspose layers in paddle.nn.layer, test=develop

* add example code in docstring, test=develop

* update unittests to work with test_runner, test=develop

* add L1Loss

* support L1Loss, test=develop

* add test, test=develop

* fix batch, test=develop

* follow comments, test=develop