提交 1de75c03 编写于 作者: H hedaoyuan 提交者: emailweixu

report error when use parallel_nn to train recurrent_nn model (#335)

上级 5f2059db
...@@ -28,6 +28,12 @@ void ParallelNeuralNetwork::init( ...@@ -28,6 +28,12 @@ void ParallelNeuralNetwork::init(
const std::vector<ParameterType>& parameterTypes, bool useGpu) { const std::vector<ParameterType>& parameterTypes, bool useGpu) {
NeuralNetwork::init(config, callback, parameterTypes, useGpu); NeuralNetwork::init(config, callback, parameterTypes, useGpu);
if (config.type() == "recurrent_nn") {
LOG(FATAL)
<< "You can not add `--parallel_nn=true` on the command line, "
<< "parallel_nn training mode does not support the recurrent_nn model.";
}
useGpu_ = useGpu; useGpu_ = useGpu;
numDevices_ = 0; numDevices_ = 0;
if (useGpu_) { if (useGpu_) {
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册