py-motmetrics

py-motmetrics copied to clipboard

how to solve this problem?

1

this is one of my result: idf1:150%；idp:150%；idr:150% idf1、idr、idp>100%.how to solve this problem? And my motp is too slow,just 0.11,but mota is 0.74

ZZHHogan

MOTP with euclidean distance metric gives mean squared distance.

1

When usign motmetrics.utils.compare_to_groundtruth() function with dist='euc', the distance metric is configured to the squared euclidean distance (norm2squared_matrix). As a consequence, the distance threshold (distth) should be the maximum **squared** distance....

angelcarro

would you please suggest code for multi camera multi object tracking evaluation

4

ssbilakeri

About HOTA

10

I am using py-motmetrics super well but in mot-challenge, it has introduced the HOTA metric. So may I ask when the HOTA will also include in this library? Thanks

FangLintao

I'm having some trouble understanding how switches are counted for the MOTA score. Let's say I have a bunch of bounding boxes with both ground truth ids as well as...

TECOLOGYxyz

I'm facing this issue while trying to evaluate the Deep Sort with Kalman Filter tracking results on MOT17 Data set 

RagabRadwan

Get ride of np.bool deprecation warning.

3

Missed another DeprecationWarning with the last one.

alexlitz

How to print IDTP, IDFP, IDTN, IDFN and num_detections metrics

1

ssbilakeri

KeyError while using compare_to_groundtruth

4

Hi, I am was trying to generate results on MOT16 challenge results and used mm.utils.compare_to_groundtruth to get the accuracy but resulted in error. ``` df_gt = mm.io.loadtxt('MOT16/preds/MOT16-01/gt/det.txt') df_test = mm.io.loadtxt('MOT16/preds/MOT16-01/gt/pretrained_pred.txt')...

amitbcp

I am trying to compute summary of several accumulators the following way: mh = mm.metrics.create() summary = mh.compute_many([all_0, all_1], names=['acc_0', 'acc_1'], metrics=METRICS_MOT, generate_overall=True) compute_many works without generate_overall, however when i...

alexgoft