Nghia Tran

Noisy edge function doesn't handle all quadrilateral shape

1

I found [buildNoisyEdges function](https://github.com/amitp/mapgen2/blob/4394df0e04101dbbdc36ee1e61ad7d62446bb3f1/NoisyEdges.as#L24) couldn't handle this form of quadrilateral because intersections of 2 lines (edge.v0, edge.v1 and edge.d0, edge.d1) will lie outside of their quadrilateral and makes its noisy...

Reproduce result for Kitti benchmark

4

@MarvinTeichmann How reproduce results in your Multinet paper? I tried to add resnet decoders and compare them with the VGG decoder but when I submit results onto http://www.cvlibs.net/datasets/kitti/, it turns...

Update evaluate_object.cpp so that it will work with dataset with similar format as Kitti

1

Basically, this PR remove hard coded numbers like N_MAXIMAGES and N_TESTIMAGES.

Incorrect Cross-validation for knn.

1

In knn.ipynb file, you have: ``` y_cross_validation_pred = classifier_k.predict_labels(X_train_folds[n], k) ``` This is incorrect because `predict_labels` takes in a distance matrix but you pass in a raw test matrix. So,...