search

RonLek / FastV2C-HandNet

Repository for the implementation of "FastV2C-HandNet: Fast Voxel to Coordinate Hand Pose Estimation with 3D Convolutional Neural Networks"
https://arxiv.org/abs/1907.06327
10 stars 2 forks source link

how to speed up training? #4

Closed LYKlyk closed 4 years ago

LYKlyk commented 4 years ago

Environment: Ubuntu RTX 2080ti 11g

When I try to train with MSRA dataset, I find that the training speed is very slow, and the batch size can only be set to 2. How can I increase the size of batch size? Why can a video card with 11g memory only read 2 batch sizes? How can I improve my training speed? How many epochs do you need to train? Thank you for response.

RonLek commented 4 years ago

Batch size can be increased through the batch_size variable in the MSRAHandDataset class in datamsra.py file. Since the dataset size is huge you would require better hardware if you wish to decrease the batch size and load the complete dataset into the memory. We have trained our network for 3 epochs after which it is found to overfit. You can find these and other details in the Implementation section of our paper.