Machine-Learning-Collection icon indicating copy to clipboard operation
Machine-Learning-Collection copied to clipboard

Published 20 hours ago • verified publisher icon aladdinpersson

Number Parameters EfficientNet-B0

Open log-layer opened this issue 4 years ago • 2 comments

Hey Aladdin, thanks for the awesome YouTube videos.

I was checking the implementation of EfficientNet that you provided, and I noticed that in the final example, the total number of parameters for EfficientNet-B0 is 14,047,366.

Is this correct? According to Table 2 of the original EfficientNet paper, I thought that Version B0 was supposed to have 5.3M parameters. Thanks in advance,

PS. In order to calculate the total number of parameters, I inserted the following line of code into the test() function: print(f'Total Number of Parameters: {sum( p.numel() for p in model.parameters() if p.requires_grad ):,}')

log-layer avatar Jun 21 '21 20:06 log-layer

Opened a new issue defining why this is happening https://github.com/aladdinpersson/Machine-Learning-Collection/issues/77

MaxVanDijck avatar Sep 23 '21 01:09 MaxVanDijck

@MaxVanDijck Thanks for the feedback.

Rafael10Diez avatar Sep 23 '21 18:09 Rafael10Diez