DeepLabCut is an efficient method for pose estimation based on deeplearing. And Google Colaboratory is free to try deeplearning with WEB. If they are connected, you can use DeepLabCut for free. But sometimes failed because environment is broken by system upgrade on Colaboratory.
DeepLabCut(2.3.8) is required tensorflow(<2.13) which CUDA version is 11.8. Google Colaboratory default CUDA version is 12.1 (2023/12/17), so cannot run training with GPU.
Following steps need to training with GPU on Colaboratory. (Run on code segment each commands.)
!apt update && apt install cuda-11-8
!pip install -U deeplabcut[tf]
import tensorflow as tf
tf.config.list_physical_devices('GPU')
If it succeeded, return follows;
[PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]Load deeplabcut.
import deeplabcut
Start training.
deeplabcut.train_network('/content/drive/MyDrive/project/config.yaml')
If it succeeded, GPU memory grows on resource monitor, and start training.