Open Onestringlab opened 11 months ago
Software: Pytorch 1.8+ and ubuntu 16.04+ Hardware: the training process needs about 20G graphics memory, our experiments are conducted on two Nvidia titan X gpus or a single 3090 gpu.
Hope these information can help you~
If I use 1 8GB GPU, can the program code still run? Or there is a configuration that needs to be changed. Thank You.
It depends on the final goal of your project. If you want to obtain a better feature extractor for SLR, it would be better to adopt GPUs with larger memory, or use much lighter backbone and lower FPS. If you want to train a SLT model, you can leverage the provided model to extract visual features, and only train the translation model based on the extracted features.
I appreciate the work you have done. Can you tell us about the hardware and software specifications used to carry out this research? What Python libraries do you use? Provide detailed requirements
I am very grateful also you want to share it.
Thank You