DeepLabCut (https://github.com/DeepLabCut/) (Mathis et al., 2018; Nath et al., 2019) was used for tracking body parts of mice in an open field arena or in the rotarod. DeepLabCut 2.1.8.2 (local version on Windows with CPU, using the GUI) and 2.1.10.2 (google colab to train the network) were used using default parameters and the pretrained resnet50 network with imgaug augmentation. Frames were extracted with the k-means method and outlier frames with the jump method. Rotarod, back camera: 20 images from 9 videos (10 fps) were extracted for a total of 180 labeled pictures. 5 body parts (2 paws, 2 ankles, tail base), 4 corners of the rotarod, 2 points on the rotarod wheels and 4 points in a flashing LED (indicating timestamps) were manually labeled. A neural network was trained using these images for 80K iterations. 20 images from 14 videos with different recording conditions were labeled. The network was trained to 200K iterations (from scratch) (train error: 3.00, test error: 3.75). Relevant videos were analyzed at each step, for a total of 152 videos. Used to analyze videos for a publication (Labouesse et al., Nature Communications 2023)