fast-rcnn-train-another-dataset icon indicating copy to clipboard operation
fast-rcnn-train-another-dataset copied to clipboard

Published 20 hours ago • verified publisher icon YihangLou

How to train on a custom dataset

Open MyVanitar opened this issue 8 years ago • 0 comments

Hello,

How can we pick-up a pre-trained model and re-train it on a custom data-set (user defined data-set)? I have selected the PVANET+ (Compressed) because as I see it shows a good combination of speed and mAP.

Questions like:

  • The Train/Test images should be annoated to what format?
  • How to created the LMDB files for PVANet after annotation? By standard Caffe tools or you have your own tool?
  • How to modify CFG / Prototxt files?

Considering that I gonna fine-tune on existing trained .caffemodels, so I must get a high accuracy even on a small dataset. Yes?

MyVanitar avatar Feb 15 '17 09:02 MyVanitar