Mike
Mike
## 🐛 Bug My trainer ```python # log locally: tb_logger = pl.loggers.TensorBoardLogger( save_dir=str(EXP_ROOT), name='my_model', default_hp_metric=False, ) # log remotely on aim server aim_logger = AimLogger( repo='aim://127.0.0.1:53800', experiment='my_model', train_metric_prefix='train_', test_metric_prefix='test_', val_metric_prefix='val_',...
deepakcrk's Yolov5m Full body eval results. `P: 0.743`; `R 0.475`; `mAP50 0.631`; `mAP50-95 0.405`
I see a lot of questions regarding performance under issues, so I am opening this just as a place for people to drop their results and discuss how they got...
Just curious. Are you working on any real-time frame-by-frame GNN approach?
I have 2 sequences which I generated motchallenge compliant results for. First lines in my `(frame, id, l, t, w, h, conf, class)` dataset format: ```bash 2,3,1436,409,159,371,0.508485,0 2,2,583,442,93,264,0.689593,0 2,1,1338,425,147,356,0.692870,0 3,3,1462,417,136,360,0.542826,0...
I am running this: ```py import os import numpy as np import motmetrics as mm def compute_motchallenge(gt_file, test_file): df_gt = mm.io.loadtxt(gt_file) df_test = mm.io.loadtxt(test_file) # Define thresholds for matching th_list...
Initialize dists to avoid UnboundLocalError when calculating HOTA. Fixes this error: https://github.com/cheind/py-motmetrics/issues/193
I noticed you recently integrated the HOTA metric into this repo. Do you plan to release a new version on PyPI soon?
### Search before asking - [X] I have searched the Yolov8 Tracking [issues](https://github.com/mikel-brostrom/yolo_tracking/issues) and found no similar enhancement requests. ### Description If you are using this repo and performing default...