How to select most suitable jetson using teraflops rating of a neural network

In our undergraduate project, we have to request a development board according to the teraflops rating of our project. currently our model is running at TX2 board and it crashes. but the board says that we have enough flop rate why this happens our model requires around 30 Gflops but jetson TX2 have 1.33Teraflops

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.


Would you mind to share more information about the error?
Do you think crash is caused by different Teraflops?

Have you maximize the device performance firs?

$ sudo nvpmodel -m 0
$ sudo jetson_clocks