Open Shaofei-Li opened 3 years ago
I have found that if I use placehoulder and feed the value to run ,and I will get zero ,but if I use array and transform it to tensor and run ,the result will be right.
make: makefile_10.0: 没有那个文件或目录 make: *** 没有规则可以创建目标“makefile_10.0”。 stop
The loss is very low at the beginning of the training process. Is this all right?
@LSFMESSI The loss is very low at the beginning of the training process. Is this all right?
When I "make -f makefile_10.0 clean" and "make -f makefile_10.0", I can use the tf_nndistance.nn_distance function ,but no matter what two sets of point clouds I enter, the returned distance and idx are zero. How can I use the function correctly?Thanks