ozgurkara99 / isnas-dip Goto Github PK

ISNAS-DIP: Image Specific Neural Architecture Search for Deep Image Prior [CVPR 2022]

License: MIT License

Python 9.21% Jupyter Notebook 90.67% Shell 0.12%

cvpr2022 dataset deep-learning dip machine-learning nas

isnas-dip's Issues

missing 'model.csv' file?

Hi authors, thanks for the interesting work. I'm trying to run the nasdip.sh, and it seems that '/home/ersin/Documents/machine learning/NAS-DIP Summer Research/benchmark/models.csv' not uploaded?

"None of ['model name'] are in the columns"

Hi @ozgurkara99, somehow I got this error when computing the metrics. It happened at random_search.py line 245. Seems that the metrics are not calculated but not sure why.

Hi @ozgurkara99, I'm wondering, how do we train on our dataset? I tried to modify the path in "utils/path.py" but it seems like the code is only taking caring of a single file with specific name (? Thank you.

.

Metrics calculated at initialization

Hi @ozgurkara99, I'm wondering about some of the details of the method: you mentioned that the metrics (PSD DB MSE etc.) were calculated at initialization with random CNN output and the corrupted image, does that mean you only passed the noise input into the model once without weight updating, and get the output from there?

Recommend Projects