search

mit-han-lab / once-for-all

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
https://ofa.mit.edu/
MIT License
1.89k stars 333 forks source link

Incorrect accuracy while testing the pretrained ofa network #8

Closed chenyaofo closed 4 years ago

chenyaofo commented 4 years ago

Thanks for sharing your code.

I have some problems when I test the ofa pretrained network.

I build a ofa network using the code provided in the README.

from model_zoo import ofa_net
ofa_network = ofa_net('ofa_mbv3_d234_e346_k357_w1.0', pretrained=True)

ofa_network.set_active_subnet(ks=7, e=6, d=4)
subnet = ofa_network.get_active_subnet(preserve_weight=True)

# test the subset on the validation set of the ImageNet

When I set the parameter ks, e and d with different value, the accuracy of the ofa network becomes about 0 in some cases. I show the test results in the following: image

Have I made some mistake while testing the ofa pretrained network?

chenyaofo commented 4 years ago

I am sorry I made some mistakes in the testing code.