hello, I am trying to train a ssd model following the guide of this lesson "Use deep learning to assess palm tree health"(https://learn.arcgis.com/en/projects/use-deep-learning-to-assess-palm-tree-health/) . I tried many times with different tile size like 448/128/256/224, different argis pro version 2.6/2.8, on different computers, but met with the sample problem. Every Epoch finished very quickly and the train loss remained 'nan'. Here is my samples and parameters. I have no idea what cause the problem. Please help me, thanks a lot.
![2.jpg 2.jpg](https://community.esri.com/t5/image/serverpage/image-id/21482i5D4E82F3FACA70C9/image-size/medium?v=v2&px=400)
![3.jpg 3.jpg](https://community.esri.com/t5/image/serverpage/image-id/21483iB6B5A270C035BB3B/image-size/medium?v=v2&px=400)
![4.jpg 4.jpg](https://community.esri.com/t5/image/serverpage/image-id/21484i0E501A0F998A63E7/image-size/medium?v=v2&px=400)
![5.jpg 5.jpg](https://community.esri.com/t5/image/serverpage/image-id/21485iC2AD7377E87A83D4/image-size/medium?v=v2&px=400)
![6.jpg 6.jpg](https://community.esri.com/t5/image/serverpage/image-id/21486i7EE9627A804B4BE4/image-size/medium?v=v2&px=400)
![7.jpg 7.jpg](https://community.esri.com/t5/image/serverpage/image-id/21487iCD80F609C41FCD08/image-size/medium?v=v2&px=400)
Dear @Anonymous User, I found you have answered a question similar with mine, I wish you could see this.