Disciple7

Results 3 comments of Disciple7

补充:以上为使用QAT量化的yolov3_mobilenet_v1_qat,导出为infer模型和serving模型运行结果。不使用TensorRT(不添加--run_mode=trt_int8或--use_trt参数时可正常运行) 后续测试了未量化的yolov3_mobilenet_v1_270e_voc模型,以及yolov3_darkenet53_270e_voc模型,在PaddleInference下进行推理,同样报Pass preln_embedding_eltwise_layernorm_fuse_pass has not been registered. 报错信息如下: ``` (pdconfig) ubuntu@sunyuke:~/lxd-storage/xzy/PaddleCV/PaddleDetection$ python deploy/python/infer.py --model_dir=./infe rence_model/yolov3_darknet53_270e_voc_origin --image_file=./dataset/fire_smoke_voc/images/00001.jpg --device=GPU -- run_mode=trt_int8 /home/ubuntu/anaconda3/envs/pdconfig/lib/python3.7/site-packages/paddle/vision/transforms/functional_pil.py:36: DeprecationWarning: NEAREST is deprecated and will be removed in Pillow...

更新一下:用[Paddle Issue#42759](https://github.com/PaddlePaddle/Paddle/issues/42759)提到的方法安装了带TensorRT的PaddleInference whl后能够成功开启trt_int8等run_mode了。但是PaddleServing依然报No OpConverter Type [nearest_interp_v2]错误。

请问这个功能有实现吗……