ruyijidan

Results 6 comments of


                                            ruyijidan

'TensorRT_model.pb' model's size is twice as large as the original pb model

my FP16 trt model is 653.5M ， I guess it‘s OK，because at GPU 970M the PFS from 10 to 20

'TensorRT_model.pb' model's size is twice as large as the original pb model

can you see the trt model fps？if you can please tell me the detail version ty!! cudann7.5.?, Tensorflow1.13.?, TensorRT5.0.?

'TensorRT_model.pb' model's size is twice as large as the original pb model

@Julyliying ty！but little obvious effect at 1080ti, cudnn7.5.1.10 Tensorflow1.13,.1 TensorRT5.1.5.0

How can I convert my own model？

model = alexnet(pretrained=True).eval().cuda() it;s regular pytorch model how can I convert my alexnet model ?

Determine the environment

try onnx=>1.2 or 1.0

human_pose_estimation C++预测接口

推荐看下Paddle-Inference-Demo https://github.com/PaddlePaddle/Paddle-Inference-Demo