使用量化压缩装载int8模型运行提示op mul Y must be the same. Get (float) != (int8_t)
Created by: Bond-H
-
系统环境:
- Paddle版本:1.5.1,CPU,无使用其他加速模块
- 系统: CentOS 6.3
-
问题描述:
-
问题复现:
git clone https://github.com/Bond-SYSU/paddle_compress.git
cd paddle_compress
sh run.sh compress # 执行模型压缩
python inference_model.py --inference_save_dir ./output/float/ # 测试float版
python inference_model.py --inference_save_dir ./output/int8/ # 测试int8版,报错