未验证 提交 02b75a50 编写于 作者: D Double_V 提交者: GitHub

Merge pull request #3293 from PaddlePaddle/LDOUBLEV-patch-1

fix precision
......@@ -164,7 +164,7 @@ def create_predictor(args, mode, logger):
config.enable_use_gpu(args.gpu_mem, 0)
if args.use_tensorrt:
config.enable_tensorrt_engine(
precision_mode=inference.PrecisionType.Float32,
precision_mode=precision,
max_batch_size=args.max_batch_size,
min_subgraph_size=args.min_subgraph_size)
# skip the minmum trt subgraph
......
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