search

vietnh1009 / SSD-pytorch

SSD: Single Shot MultiBox Detector pytorch implementation focusing on simplicity
MIT License
164 stars 49 forks source link

training with a custom dataset #2

Closed abdo-ameen closed 3 years ago

abdo-ameen commented 3 years ago

I have two questions, how can I use this code to train the SSD with my own custom dataset? and after finishing the training process, how can I use the model for inference tasks on real-time camera applications? thank you for simplifying the SSD idea, I'm a beginner and I'm finding the existing implementations really complicated.

vietnh1009 commented 3 years ago

Hi,

  1. You need to write your own dataloader, based on mine for COCO
  2. If you need to run it in real device, I think you need to convert the trained model to onnx or tensorrt. Unfortunately I cant not provide detail step for it. Bests,