Artsiom

BUG in computeGaussianPerplexity when K > N - 1

1

In line [tsne.cpp#L37](https://github.com/DmitryUlyanov/Multicore-TSNE/blob/master/multicore_tsne/tsne.cpp#L374) vectors `indices` and `distances` will have `< K + 1` elements if `K > N - 1`. This will cause erroneous reads out of the bounds of...

STD output is not captured 40% of the times

3

Sacred version: `0.7.1` Python: `2.7.11` Ubuntu `14.04` 2 out of 5 times the field `captured_out` in the mongoDB entry doesn't contain strings which I print to stdout with `print` Minimal...

How to look at the loss value?

9

Is there a possibility to print the loss value during the optimization process? Or at least after the last epoch? It would make sense to add this feature, as it...

Hey, Could you please refer to the table which lists the accuracies of the pretrained models when evaluated on Imagenet using a linear classifier?

Evaluation protocol for PKU VehicleID dataset

1

Hi, Thanks for a nice contribution! Could you please share the routine for the evaluation on PKU VehicleId dataset? Or is it the same as you have for CUB-200-2011? We...

BUGFIX. Unused variable removed, that caused quadratic running time o…

1

1. Fixed BUG, that caused looping over all dataset every time we applied SVM to an image during mining of negatives. Running time improved from quadratic to linear. 2. Optimized...

Updated branch with latest commits from https://github.com/BVLC/caffe master . Tested on compatibility with https://github.com/yosinski/deep-visualization-toolbox master branch.

Thank you for the code and a nice paper. I'm using your code from https://github.com/chaoyuaw/incubator-mxnet/tree/master/example/gluon/embedding_learning I wonder if you have tried training the networks other than `Resnet50_V2` using the proposed...