Ze Yang comments

Results 4 comments of


                                            Ze Yang

For a machine with 4 GPUs, the program spends roughly 4GB for each GPU.

@Xiaoccer I do not want to change the data distribution of training images and testing images. So I use the cropping strategy.

I think you need to change the ProposalNet code in core/model.py, which by default generates the proposals in different sizes.

Thanks for your clarification.