geekfreak issues

Repositories
Issues
Comments

Results 2 issues of


                                            geekfreak

FLOPS calculation

Hi, I notice you are calculating MACS in your profile_model.py. Did you report the MACS value as the GFLOPs? The reported GFLOPs in your paper does not match my calculation.

When training, why it requires the pre-trained model to be put in the output directory?

I attempted to run the training experiments of ROLO, Taking experiments/training/ROLO_step1_train_30_exp2.py for example: after I set the `rolo_weights_file = 'output/ROLO_model/model_step1_exp2.ckpt` in line 63 to a local directory that I created,...