Performance of trained model weights
Closed this issue · 2 comments
Hi,
thanks for making your code public.
I was wondering if there are performance stats to the trained model weights you offer? Would be great for deciding which weights to use for experiments.
Hello.
d2_ots.pth
are simply the off-the-shelf Caffe weights pretrained on ImageNet. By default, at the moment, you should use the model fine-tuned on the entire MegaDepth - d2_tf.pth
(i.e. the one used by the feature extraction - extract_features.py
- script with default parameters). The model fine-tuned without the PhotoTourism scenes was only released in order to have a fair comparison on the Image Matching Workshop Benchmark - https://image-matching-workshop.github.io/. We plan on releasing new models in the future and we will include a more detailed comparison at that point in time.
Thanks for the detailed answer.