search

open-mmlab / mmtracking

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
https://mmtracking.readthedocs.io/en/latest/
Apache License 2.0
3.52k stars 591 forks source link

prev_img_prefix, prev_img_name = prev_img_meta[ ValueError: not enough values to unpack (expected 2, got 1) #894

Open yinxingshu41 opened 1 year ago

yinxingshu41 commented 1 year ago

An error occurred while running mmtracking on the Windows system, and the configuration file is using qdtrack Faster rcnn R101 Fpn 24e_ Lvis.py, training was conducted on the lvis dataset, with the test set being TAO validation. However, an error occurred while running python tools/test. py: [] 40/36375, 3.7 task/s, delayed: 11s, ETA: 9843sTraceback (most recent call last):

File "E: ComputerVision 8mmtracking mmtracking master tools test. py", line 236, in

Main()

File "E:\ComputerVision\mmtracking-master\tools\test. py", line 186, in main

Outputs=single GPU Test（

File "E:\ComputerVision\8mmtracking\mmtracking\master\mmtrack\apis\test. py", line 84, in single GPU Test

Prev Img Prefix Img Name=prev Img Meta[

ValueError: not enough values to unpack (expected 2, got 1).

This error appears in the 40th image. How can I resolve it?

jangbi1 commented 10 months ago

I have same errors. Do you solve it?