This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
Part Number: PROCESSOR-SDK-DRA8X
Tool/software: TI C/C++ Compiler
Hello,
I have two questions regarding the TI models:
1. What is the maximum size of a TI model that can be loaded into the memory, and run on the EVM ?
2. Is it possible to convert Yolo model to TI model ? I couldn't find any info in docs which is related to Yolo.
Thanks,
Alex
Alex,
[1] Memories are dynamically assigned by the Alg layer at runtime, and therefore there is no hard limit on the model size, but should be decided while the network in run.
[2] YOLO model can be converted to TIDL as it is based on convolution layers. It is not validated with TIDL.
- Subhajit
We need assistance in defining pipeline configuration file for Yolo model.
Do you have an example for Yolo model import ?
No, as I mentioned earlier, we have nnot validated YOLO models and therefore do not have validated examples
- Subhajit