How To Obtain Seed Model?

[bajinsheng]

Hi!
For this command

python emi_mutate.py --model_name [model-name] --seed_model_path [path for seed ONNX model] --input_data_path [default is ../data/data.npy] --seed_number [seed_number]

How do I obtain the data.npy and other onnx models? They are not included in the google drive.
Thanks!

[Wilbur-Django]

The link is updated now.

[bajinsheng]

Thanks for your reply. However, it is a corrupted zip archive:

$ unzip data.zip
Archive:  data.zip
  End-of-central-directory signature not found.  Either this file is not
  a zipfile, or it constitutes one disk of a multi-part archive.  In the
  latter case the central directory and zipfile comment will be found on
  the last disk(s) of this archive.
unzip:  cannot find zipfile directory in one of data.zip or
        data.zip.zip, and cannot find data.zip.ZIP, period.

[Wilbur-Django]

Thanks for pointing out. After some investigation, I find vgg11.onnx in the zip file cannot be correctly extracted. You can use 360zip on Windows to extract the other four files.

Currently, I cannot find a backup of the original vgg11.onnx on my computer. Could you please try exporting a VGG11 model from Pytorch 1.7 to ONNX?

[Wilbur-Django]

I'm not sure whether it's due to some issues with the zip program during the packaging process. Previously, another independently packaged zip file of my data is also seen to be corrupted.

[bajinsheng]

fastjar xvf data.zip

I found that fastjar can uncompress this corrupted zip file.