once-for-all

once-for-all copied to clipboard

KeyError: <InterpolationMode.BILINEAR: 'bilinear'>

4

when running train_ofa_net.py torch 1.11.0 torchvision 0.12.0

talenz

Hi，I found that the `expand_ratio` passed in mobilnetV2 will keep the same number in all stages and cells, is this a bug? https://github.com/mit-han-lab/once-for-all/blob/80a2e26ef04426213ad836b056234914d33a3c36/ofa/imagenet_classification/networks/proxyless_nets.py#L176

zhanglei1172

NoneType error when run torch.jit.script()

1

Hello, I want to optimize the OFA subnet model but I meet the error: ``` Traceback (most recent call last): File "mobile_test.py", line 129, in data_loader,bn_list[0],net_config)) File "mobile_test.py", line 62,...

YuantianGao

Question about the calculation of importance(L1 Norm)

1

Thank you for your great job. I have a question about the calculation of importance. Here in Once for all, the importance is calculated by the input dimension. https://github.com/mit-han-lab/once-for-all/blob/cfa0722d57e3a2391eb36b8cf613dd17ff7a32ae/ofa/imagenet_classification/elastic_nn/modules/dynamic_layers.py#L263 But...

pprp

How to train my own acc predictor and efficiency predictor

2

I have trained OFA network on the custom dataset. However, how to train my own acc predictor and efficiency predictor

Xingxu1996

Could you share how to calculate mean, std and count in mobile_trim.yaml? And what does it meaning? I want to change the width_mult to 0.5, but tje output_feature will be...

TomHsu-MIddle

The effect of the `base_acc` in accuracy_predictor ?

3

Hi, I noticed that here(link1) add base acc to train accuracy predictor and set the last linear layer bias as False. For the same batch data, they have the same...

lucienne999

ImportError: cannot import name 'MyRandomResizedCrop'

1

`/opt/vitis_ai/conda/envs/vitis-ai-pytorch/lib/python3.6/site-packages/ofa/imagenet_classification/run_manager/run_manager.py in 17 from ofa.utils import get_net_info, cross_entropy_loss_with_soft_target, cross_entropy_with_label_smoothing 18 from ofa.utils import AverageMeter, accuracy, write_log, mix_images, mix_labels, init_models ---> 19 from ofa.utils import MyRandomResizedCrop 20 21 __all__ = ['RunManager']...

dongzhang2021

When I train with two cards on my machine with `horovodrun -np 2 -H localhost:2 python train_ofa_net.py`, The code works fine. But I found that the memory of both processes...

Hukongtao

I am trying to obtain specialised deployment with MobileNetV3 architecture, but I obtain the following the error. Kindly suggest on what must be done. The error originates from this code:...

akvallapuram