security_vision/Towards-Realtime-MOT
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

fixed a spelling mistake

Browse source
This commit is contained in:
Zhongdao 2020-01-10 13:29:56 +08:00
parent 822abfffc7
commit 27809fd27b
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

@ -39,7 +39,7 @@ JDE-1088x608-uncertainty: [[Google Drive]](https://drive.google.com/open?id=1nln
- Edit `cfg/ccmcpe.json`, config the training/validation combinations. A dataset is represented by an image list, please see `data/*.train` for example. - Edit `cfg/ccmcpe.json`, config the training/validation combinations. A dataset is represented by an image list, please see `data/*.train` for example.
- Run the training script: - Run the training script:
``` ```
CUDA_VISIBLE_DEIVCES=0,1,2,3,4,5,6,7 python train.py CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python train.py
``` ```
We use 8x Nvidia Titan Xp to train the model, with a batch size of 32. You can adjust the batch size (and the learning rate together) according to how many GPUs your have. You can also train with smaller image size, which will bring faster inference time. But note the image size had better to be multiples of 32 (the down-sampling rate). We use 8x Nvidia Titan Xp to train the model, with a batch size of 32. You can adjust the batch size (and the learning rate together) according to how many GPUs your have. You can also train with smaller image size, which will bring faster inference time. But note the image size had better to be multiples of 32 (the down-sampling rate).