mit-han-lab/once-for-all
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
PythonMIT
Issues
- 4
KeyError: <InterpolationMode.BILINEAR: 'bilinear'>
#70 opened by talenz - 0
- 2
Use for our Custom Dataset
#52 opened by Darshcg - 0
LatencyTable Target Hardware Error
#89 opened by hasanberatsoke-cy - 1
imagenet_1k.zip
#80 opened by atdovas - 0
Resnet50 Access Denied
#88 opened by hasanberatsoke-cy - 3
Can't download `ofa_resnet50` super network
#83 opened by macsz - 2
- 0
How do i specialize OFA for cifar10
#85 opened by amitpant7 - 2
Why only 3x3 kernel size in resnet?
#55 opened by tfwang08 - 1
Using Once-for-all for a custom CNN
#72 opened by just-an-intern - 0
[Easy fix] OFA Tutorial On colab
#81 opened by IHIaadj - 0
Missing dependency numpy
#78 opened by radomirbosak - 0
About the pre-trained hypernetwork used for the results in Table 1, is it ofa_mbv3_d234_e346_k357_w1.0 or ofa_mbv3_d234_e346_k357_w1.2?
#76 opened by yuny220 - 0
- 1
error when custom sub sampling a model
#74 opened by MMorafah - 2
torch.hub example is broken
#73 opened by NicolasHug - 0
expand_ratio BUG?
#71 opened by zhanglei1172 - 1
NoneType error when run torch.jit.script()
#58 opened by YuantianGao - 1
- 0
How to cal calculate the mobile_trim.yaml?
#69 opened by TomHsu-MIddle - 3
- 1
- 0
All memory on one card
#68 opened by Hukongtao - 0
How to train the supernet?
#64 opened by Hukongtao - 0
- 2
Some doubts about the predictior
#53 opened by qiuqi1207 - 4
cannot run colab example code
#61 opened by mistake0316 - 5
What should I do after train_ofa_net
#57 opened by detectRecog - 0
Is set_running_statistics necessary when we evaluate the subnet if we don't change expand ratio in OFA ?
#60 opened by zshanwei - 0
Which evolution algorithm do you use?
#59 opened by ifed-ucsd - 3
- 4
How to export one of the subnets?
#51 opened by gianderiu - 1
what does MACs mean?
#56 opened by Edwardmark - 2
How to generate latency_table?
#46 opened by tfwang08 - 4
- 1
subnet重训练代码
#41 opened by johsnows - 3
- 0
top5 performance
#49 opened by bknyaz - 0
Question about args.dynamic_batchsize
#48 opened by ShoufaChen - 0
How to measure the latency correctly?
#47 opened by tfwang08 - 3
- 0
Questions about training supernet
#45 opened by zhiheng-ldj - 0
Why not try to search on Anynet design space.
#43 opened by PistonY - 1
args.valid_size is wrong?
#39 opened by gegeo0 - 3
About model converter code (Pytorch to Tensorflow-Lite) for on-device inference latency test.
#35 opened by gunjupark - 1
When I use ofa_resnet50 to Efficient Deployment in tutorial/ofa.ipynb, I met some errors.
#40 opened by darrenzhang1007 - 0
- 1
cannot import MyRandomResizedCrop from ofa.imagenet_classification.data_providers.base_provider
#34 opened by psammy007 - 0