This is the optimal workstation configuration for DeepLabCut, which is widely used in animal behavior analysis and neuroscience research.
DeepLabCut handles high-resolution videos and large amounts of image data, so the VRAM (video memory) on the GPU is important. By using the GPU, learning and inference processing becomes faster than when using only the CPU.
Computer Hardware:
Ideally, you will use a strong NVIDIA GPU with at least 8GB memory. A GPU is not necessary, but on a CPU the (training and evaluation) code is considerably slower (10x) for ResNets, but MobileNets are faster (see WIKI). You might also consider using cloud computing services like Google cloud/amazon web services or Google Colaboratory.
Reference: How To Install DeepLabCut — DeepLabCut
This configuration uses the Intel Core Ultra 9 285K, which provides a good balance between core count and clock speed, as well as the NVIDIA GeForce RTX5090 32GB.
| CPU | Intel Core Ultra 9 285K 3.70GHz(8C/8T)+3.20GHz(16C/16T) |
| memory | Total 128GB DDR5 6400 32GB x 4 |
| storage | 1TB SSD M.2 NVMe Gen4 |
| Video | NVIDIA GeForce RTX5090 32GB |
| network | on board(2.5GBase-T x1) Wi-Fi, Bluetooth |
| Housing + power supply | Mid-tower case 1500W 80PLUS PLATINUM |
| OS | Microsoft Windows 11 Professional 64bit |
Related information
Choosing a workstation suitable for behavioral psychology and animal behavior analysis
DeepLabCut Turnkey System (KineAnalyzer × DeepLabCut)
- Tips on installing hardware for DeepLabCut
- Running video learning with DeepLabCut on multiple GPUs
- I tried training DeepLabCut to learn typing videos
- Improving learning accuracy in DeepLabCut
- DeepLabCut Training time comparison by resolution and GPU and optimal GPU specifications
|
■ Click here for details and inquiries about this PC case
* Please enter the name of the case or your desired conditions. |
