training and testing on the terminal ?

[shengyuwoo]

What are the instructions for running training and testing on the terminal? Can you give me some information?

[miautoml]

Thanks for asking. The evaluation command is just updated. For training, please refer our paper for more information.

[shengyuwoo]

Thanks for asking. The evaluation command is just updated. For training, please refer our paper for more information.

I think you should write the setup structure of a Dataset, including the path of the model.
I just tried this verification instruction. This problem arises: verify.py: error: argument -- model: invalid choice:'[MoGA_A'(choose from'MoGA_A','MoGA_B','MoGA_C').

[miautoml]

@shengyuwoo Proper modification is required. Note [MoGA_A|MoGA_B|MoGA_C] means you should pick one model, either MoGA_A or the others. For the dataset structure, please follow the setting in FairNAS .

[shengyuwoo]

@shengyuwoo Proper modification is required. Note [MoGA_A|MoGA_B|MoGA_C] means you should pick one model, either MoGA_A or the others. For the dataset structure, please follow the setting in FairNAS .

I found that the three pre-training model files you provided were problematic. I downloaded them and unzipped them to show empty files.

[miautoml]

@shengyuwoo It is zipped with the default macOS compress tool. I don't seem to reproduce your problem. Could you show me how do you unzip the files?

[shengyuwoo]

@shengyuwoo It is zipped with the default macOS compress tool. I don't seem to reproduce your problem. Could you show me how do you unzip the files?

I use the command : tar -xvf MoGaA.pth.tar to unzip on ubuntu or try to unzip on windows, but all of failed.

[shengyuwoo]

@shengyuwoo It is zipped with the default macOS compress tool. I don't seem to reproduce your problem. Could you show me how do you unzip the files?

The contents of the extracted file are displayed empty.

[miautoml]

@shengyuwoo Note MoGaA.pth.tar should be used as it is, there is no need to untar it. So the right way is --pretrained-path MoGaA.pth.tar. Good luck!