Bradley Aaron Kohler

Thanks for the response. I tried `inference.loopy_belief_propagation`. However, I've run into another error. Is `model` what I think it is? An arbitrary structured graph? ```python # Perform loopy-belief propagation on...

@mercicle, I wasn't able to get this implementation of loopy belief propagation working. Of course I appreciate the authors work, but there are other tools for doing the same loopy...

I'll address these in order. 1. It is possible to do this. However, a "saved" track is usually referred to as a "lost" track. However I doubt this will give...

ResNet is the CNN used to generate descriptors for the bounding box images. To use grayscale images you will have to retrain the CNN if ResNet does not suffice _as...

Good observation, the cost is a value in [0, 2]. Think of the cost as a _remap_ of the similarity. If the similarity is in [-1, 1], then the cost...

I think you are mistaken. The mAP score is not computed in any SORT algorithm; DeepSORT or SORT. It is a metric used to grade the CNN. This has nothing...

Those factors initialize the coveriance matrix using scalar multiples of the bounding box height. A solid way of initializing the covariance matrix given that no depth information is included in...

`_std_weight_position` and `_std_weight_velocity` are scalars multiplied with the height of the bounding box, a solid way to initialize the covariance matrix given that images have no depth information. Making these...

It is not a "callback", it is a "callable", as in a function. I'm guessing the definition in the code does not suffice? https://github.com/nwojke/deep_sort/blob/280b8bdb255f223813ff4a8679f3e1321b08cdfc/deep_sort/linear_assignment.py#L18 If you want a better definition...

Cholesky decomposition is faster than inverting a matrix using Gauss-Jordan elimination in most cases. There are several ways to decompose a matrix as well as compute the inverse. Generally, computing...