sun
sun
I met the same problem by myselfmodel: INFO:tensorflow:Channel pruning the model/MobilenetV2/Conv_1/Conv2D layer, the pruning rate is 0.265625 INFO:tensorflow:Actural preserv ratio: 0.265625 INFO:tensorflow:state is [[1. 0.5 1. 0.01785714 0.01785714 0.5 0.14138546...
yes，besides，with enbl_dst
sorry，I am afraid I don‘t have the right
anyone can help me？
I meet the same problem
@quic-bharathr i met the same problem,ldd show my GLIBC is 2.23 /* GNU ld script Use the shared library, but some functions are only in the static library, so try...
I met the same problem,and I use tf_slim build my backbone model，and my aimet version is 1.19.1pro，here is my error log： 2022-03-11 06:53:18,385 - Utils - INFO - ...... subset...
好多语法错误呀，老哥是不是用的nodepad++编辑的，比如说 train 127行 else那里少了个冒号
你好，topk4换成卷积是采用conv1x1 然后channel改成4这样修改吗？我看到论文的也是在想这个topk的部署问题
还没有尝试修改bn，我时在另外的框架实现的，没有基于作者的代码训练。根据之前的分割网络的经验，GN改BN会有一些掉点