Scially

当我把损失函数换为： ```python loss = t.mean((y_pred - y) ** 2) ``` 可以收敛。

1. 您好，关于第一点，已经在代码上解决，https://github.com/scially/Cesium3DTilesConverter/blob/master/include/GDALWrapper.h#L18-L20 2. 第三点是因为解析的时候就是按照三角面片解析的，后面我优化下 3. 第二点是什么错误提示呢？

有用最新的版本试下么。

暂时没有

有考虑，参考这个问题第三点，https://github.com/scially/Cesium3DTilesConverter/issues/5#issuecomment-1091748015

When I used this [SLD](https://github.com/locationtech/geowave/blob/master/examples/data/slds/DistributedRender.sld), I found that the CPU of the RegionServer was all 0%. . .

Hello，rfecher，when i execute geowave-examples , i find a problem  I found the cause of the problem，but i can't solve it, so i have to ask for your help The...

ok... thank you...

Thank you very much, this is exactly what I need, then I will give you feedback on the results.

i submit my job to yarn ,but there are one error: `java.lang.NullPointerException at org.locationtech.geowave.core.index.persist.PersistenceUtils.fromBinary(PersistenceUtils.java:148)` ``` 18/12/17 18:21:51 ERROR yarn.ApplicationMaster: User class threw exception: java.lang.NullPointerException java.lang.NullPointerException at org.locationtech.geowave.core.index.persist.PersistenceUtils.fromBinary(PersistenceUtils.java:148) at org.locationtech.geowave.core.store.index.PrimaryIndex.fromBinary(PrimaryIndex.java:93) at...