Skip to content

Commit 4f7916b

Browse files
committed
fix common
Signed-off-by: zehao-intel <zehao.huang@intel.com>
1 parent 38fdcff commit 4f7916b

File tree

2 files changed

+3
-3
lines changed

2 files changed

+3
-3
lines changed

examples/3.x_api/pytorch/cv/mixed_precision/README.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -36,9 +36,9 @@ bash run_autotune.sh --input_model=resnet18 --dataset_location=/path/to/imagenet
3636
## Benchmark
3737
```Shell
3838
# run optimized performance
39-
bash run_benchmark.sh --input_model=resnet18 --dataset_location=/path/to/imagenet --mode=performance --batch_size=1 --optimized=true --iters=500
39+
bash run_benchmark.sh --input_model=resnet18 --dataset_location=/path/to/imagenet --mode=performance --batch_size=100 --optimized=true --iters=500
4040
# run optimized accuracy
41-
bash run_benchmark.sh --input_model=resnet18 --dataset_location=/path/to/imagenet --mode=accuracy --batch_size=100 --optimized=true
41+
bash run_benchmark.sh --input_model=resnet18 --dataset_location=/path/to/imagenet --mode=accuracy --batch_size=1 --optimized=true
4242
```
4343

4444

neural_compressor/common/utils/constants.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@
3737
AUTOROUND = "autoround"
3838
FP8_QUANT = "fp8_quant"
3939
MX_QUANT = "mx_quant"
40-
MIX_PRECISION = "mix_precision"
40+
MIXED_PRECISION = "mixed_precision"
4141

4242
# options
4343
import datetime

0 commit comments

Comments
 (0)