search

ardianumam / Tensorflow-TensorRT

This repository is for my YT video series about optimizing a Tensorflow deep learning model using TensorRT. We demonstrate optimizing LeNet-like model and YOLOv3 model, and get 3.7x and 1.5x faster for the former and the latter, respectively, compared to the original models.
303 stars 110 forks source link

using other models from TensorFlow object detection zoo. #8

Closed isra60 closed 5 years ago

isra60 commented 5 years ago

Hi I'm trying to use other models from

https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md

But I don't know if the jupyter code is compatible with this?? For example with ssd_mobilenet 2. The tar.gz that you download has other files apart from interference_graph.pb like meta files and checkpoint.

ardianumam commented 5 years ago

TensorRT pb model is exactly same with standard tensorflow (TF) pb model (in term of how we use it for inference). If you can use TF zoo pb model for inference, then, yes, you can optimize to TensorRT pb model and use it for inference with possibly higher FPS.