When I used this web(jetson-inference/pytorch-collect.md at master · dusty-nv/jetson-inference · GitHub) to train googlenet, how can I record top1 and top5 accuracy like below this top picture(jetson-inference/pytorch-plants.md at master · dusty-nv/jetson-inference · GitHub)?
How can I let camera’s detection rate be high like below this buttom picture(jetson-inference/pytorch-plants.md at master · dusty-nv/jetson-inference · GitHub)? Do I set my database?