未验证 提交 4438acfd 编写于 作者: C cuicheng01 提交者: GitHub

Merge pull request #2361 from TingquanGao/dev/tipc_fix_log_path

turn off the mkldnn and trt in ConvNeXt infer
......@@ -208,8 +208,8 @@ for batch_size in ${batch_size_list[*]}; do
for ((i=1; i <=$copy_num; i++));do
cat val_list.txt >> train_list.txt
done
else
ln -s val_list.txt train_list.txt
else
ln -s val_list.txt train_list.txt
fi
cd ../../
fi
......
......@@ -39,10 +39,10 @@ infer_export:True
infer_quant:Fasle
inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=256 -o PreProcess.transform_ops.1.CropImage.size=224
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:True|False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:1|6
-o Global.batch_size:1|16
-o Global.use_tensorrt:True|False
-o Global.use_tensorrt:False
-o Global.use_fp16:True|False
-o Global.inference_model_dir:../inference
-o Global.infer_imgs:../dataset/ILSVRC2012/val
......@@ -51,4 +51,4 @@ inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.tran
null:null
null:null
===========================infer_benchmark_params==========================
random_infer_input:[{float32,[3,224,224]}]
\ No newline at end of file
random_infer_input:[{float32,[3,224,224]}]
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