mirrors
/
deep-person-reid
mirror of https://github.com/KaiyangZhou/deep-person-reid.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

update readme: add comment to train vidreid

pull/119/head
KaiyangZhou 2018-12-11 18:01:21 +00:00
parent bcd23aa3c8
commit ca90485df6
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -125,7 +125,7 @@ In addition, there is an argument called `--always-fixbase`. Once activated, the
`htri` requires adding `--train-sampler RandomIdentitySampler`.
#### Training video-reid models
For video reid, `test-batch-size` refers to the number of tracklets, so the real image batch size is `--test-batch-size * --seq-len`.
For video reid, `test-batch-size` refers to the number of tracklets, so the real image batch size is `--test-batch-size * --seq-len`. As the training follows the image-based paradigm, the semantic meaning of `train-batch-size` does not change.
### Test