We want to convert some models trained by mxnet1.5.0 to tensorrt7.0 through onnx-tensorrt(7.0) to speed up the inferece. But there are some questions about deconvolution. If there are other operations follow deconvolution, for example convolution, the inference of the model may has slower speed and lager gpu memory. The comparisons between them are as follows.
mxnet speed: 21.4385s/100 gpu_memory: 1745M
tensorrt speed: 39.9927s/100 gpu_memory: 1631M
mxnet speed: 22.1862s/100 gpu_memory: 1745M
tensorrt speed: 41.0732s/100 gpu_memory: 2653M
mxnet speed: 20.6279s/100 gpu_memory: 1745M
tensorrt speed: 38.6454s/100 gpu_memory: 1627M
mxnet speed: 67.3117s/1000 gpu_memory: 1741M
tensorrt speed: 56.8737s/1000 gpu_memory: 1625M
We think it is strange thant the performance in tensorrt cannot be better than mxnet.
Any help is appreciated. Thank You!