Closed DonMuv closed 2 years ago
Hi. Please see https://github.com/QVPR/Patch-NetVLAD/issues/24 - just use the Nanne repo, the trained model can then be PCA-ed using add_pca.py. Feel free to reopen if you have more questions.
Hi, When adding the PCA, I should use pitts30's training set instead of mapillary, right?
Hi. You can apply PCA in both cases; the training dataset does not matter.
Sure, but in: https://github.com/QVPR/Patch-NetVLAD/blob/d2b341eb5128c4e3e953f0e6afb9c27aa48698a1/add_pca.py#L125-L129 the dataset is fixed as mapillary, so I need to modify the code in order to use a dataset that's compatible with Pittsburgh, right?
Ah, I see what you mean. Indeed the code needs modification at this spot.
@StephenHausler - shall we sit together to amend the code so that at least for PCA we also enable Pitts?
Would be super good!
@Tobias-Fischer yep lets do that
HI, Can the add_pca.py be used on the pitts30 dataset?Does pca_train_set use the pitts30's training set?