-
Look at this , this has the Imagenet PCA values
https://github.com/HaixinShi/ML_Project2/blob/1fb5408802308b439c8f8baf693dd5705f8134e2/ref_codes/ZenNAS/DataLoader/__init__.py
-
{"format":"img","model":"DS3622xs+","version":"7.2.2-72806-0","addons":"acpid,cpuinfo,powersched"}
-
{"format":"dyn","model":"DS3622xs+","version":"7.0.1-42218-0","addons":"acpid,cpuinfo,powersched"}
-
Hello， Can i do Nas for myself data set based on your source code？
-
Could you please turn this into a pypi package? So that it is easy to use these models in other codebases.
-
Thank you for sharing your code.
I've tried reproducing your results using the training hyperparameters from the paper but was unable to.
I used the popular timm package for training (https://githu…
-
Can you please support choosing the number of channels? I have 1 channel input.
EfficientNet allows you to specify the number of input channels, for example if the image is grayscale.
https://gi…
-
-
https://github.com/idstcv/ZenNAS faster, bigger and more precise versions of GPU-Efficient-Networks ( https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/byobnet.py ).
-
Hi,
Why is no_create=False and no_reslink=True in the compute_ nas_score function on line 121?
I understand that making no_reslink=True removes residual connections from the model but I don't un…