I’m currently working on an AI project using an NVIDIA Jetson Nano (4GB) and TensorFlow 2 where we were planning on using a Faster R-CNN Inception ResNet V2 640x640 model. We tried using TF-TRT to reduce the network, but it seems to be too big to fit in, the vRAM memory is not big enough and using Swap doesn’t solve the issue.
We have done several tests and, for the moment, the heaviest network from the TensorFlow Model Zoo we managed to get working is the SSD MobileNet V2 FPNLite 640x640.
I’ve been searching for a list of networks that have been tested on this device for TF2, but I can’t seem to find it. I know of the existence of this list, but it is for TF1 and doesn’t involve the TF2 Model Zoo models.
Is there any chance that a list of working models with their speed, memory usage and mAP tested on a common dataset (COCO or similar) will be developed? This would be specially interesting regarding the different methods available to deploy a model, either via CPU, optimized CPU with TFLite, GPU, optimized GPU with TF-TRT, fully optimized with pure TensorRT or any other possible option that I haven’t considered.
It seems to be a somewhat-common issue, all non-experts feel a bit lost, me included.
Thank you in advance.