kmario23의 답변은 정확합니다. 기본적으로 gen_* 패키지에 대한 참조를 볼 때 자동으로 생성 된 Python 코드를 의미합니다.
def _softmax_cross_entropy_with_logits(features, labels, name=None):
r"""Computes softmax cross entropy cost and gradients to backpropagate.
Inputs are the logits, not probabilities.
Args:
features: A `Tensor`. Must be one of the following types: `half`, `float32`, `float64`.
batch_size x num_classes matrix
labels: A `Tensor`. Must have the same type as `features`.
batch_size x num_classes matrix
The caller must ensure that each batch of labels represents a valid
probability distribution.
name: A name for the operation (optional).
Returns:
A tuple of `Tensor` objects (loss, backprop).
loss: A `Tensor`. Has the same type as `features`. Per example loss (batch_size vector).
backprop: A `Tensor`. Has the same type as `features`. backpropagated gradients (batch_size x num_classes matrix).
"""
_ctx = _context.context()
if _ctx.in_graph_mode():
_, _, _op = _op_def_lib._apply_op_helper(
"SoftmaxCrossEntropyWithLogits", features=features, labels=labels,
name=name)
_result = _op.outputs[:]
_inputs_flat = _op.inputs
_attrs = ("T", _op.get_attr("T"))
else:
_attr_T, _inputs_T = _execute.args_to_matching_eager([features, labels], _ctx)
(features, labels) = _inputs_T
_attr_T = _attr_T.as_datatype_enum
_inputs_flat = [features, labels]
_attrs = ("T", _attr_T)
_result = _execute.execute(b"SoftmaxCrossEntropyWithLogits", 2,
inputs=_inputs_flat, attrs=_attrs, ctx=_ctx,
name=name)
_execute.record_gradient(
"SoftmaxCrossEntropyWithLogits", _inputs_flat, _attrs, _result, name)
_result = _SoftmaxCrossEntropyWithLogitsOutput._make(_result)
return _result
을하지만이 기능은 네이티브 C에 대한 래퍼 ++ 구현이기 때문에, 당신은 실제 C++ 코드를보고 관심이있을 수 있습니다이 경우
, 그것은 gen_nn_ops.py입니다. 그것은 CPU와 GPU 모두, tensorflow/core/kernels/xent_op.cc에 있어요 :
template <typename Device, typename T>
class SoftmaxXentWithLogitsOp : public OpKernel {
public:
explicit SoftmaxXentWithLogitsOp(OpKernelConstruction* context)
: OpKernel(context) {}
void Compute(OpKernelContext* context) override {
const Tensor& logits_in = context->input(0);
const Tensor& labels_in = context->input(1);
OP_REQUIRES(context, logits_in.IsSameSize(labels_in),
errors::InvalidArgument(
"logits and labels must be same size: logits_size=",
logits_in.shape().DebugString(), " labels_size=",
labels_in.shape().DebugString()));
OP_REQUIRES(context, TensorShapeUtils::IsMatrix(logits_in.shape()),
errors::InvalidArgument("logits must be 2-dimensional"));
// As we already tested that both inputs have the same shape no need to
// check that "labels" is a matrix too.
// loss is 1-D (one per example), and size is batch_size.
Tensor scratch;
OP_REQUIRES_OK(
context, context->allocate_temp(DataTypeToEnum<T>::value,
TensorShape({logits_in.dim_size(0), 1}),
&scratch));
Tensor* loss_out = nullptr;
OP_REQUIRES_OK(context,
context->allocate_output(
0, TensorShape({logits_in.dim_size(0)}), &loss_out));
Tensor* back_out = nullptr;
// Try to reuse the logits_in buffer for the backprop output.
OP_REQUIRES_OK(context, context->forward_input_or_allocate_output(
{0}, 1, logits_in.shape(), &back_out));
functor::XentFunctor<Device, T> functor;
functor(context->eigen_device<Device>(), logits_in.matrix<T>(),
labels_in.matrix<T>(), scratch.matrix<T>(), loss_out->vec<T>(),
back_out->matrix<T>());
}
};
당신이 깊은 다이빙 관심이 있다면, 주요 통화가 마지막 줄에 있습니다 functor(...), functor이 XentFunctor<Device, T>입니다. 실제 논리는 타사 Eigen 라이브러리로 전달됩니다. this very similar question을 참조하십시오. 끝 부분에 얼마나 깊은지를 보여줍니다.