提交 531f4a15 编写于 作者: T tensor-tang

Merge branch 'fuse/repeatedfcrelu' into fuse/second_order_mul_sub

......@@ -164,6 +164,9 @@ TEST(Analyzer_seq_pool1, compare) {
std::vector<std::vector<PaddleTensor>> input_slots_all;
SetInput(&input_slots_all);
// the output is -338405.2812, refer is -338405.21875
// so acc should be adjust
FLAGS_accuracy = 1e-1;
CompareNativeAndAnalysis(
reinterpret_cast<const PaddlePredictor::Config *>(&cfg), input_slots_all);
}
......
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