search

swz30 / MIRNet

[ECCV 2020] Learning Enriched Features for Real Image Restoration and Enhancement. SOTA results for image denoising, super-resolution, and image enhancement.
Other
667 stars 96 forks source link

number of parameters #8

Closed tuvovan closed 3 years ago

tuvovan commented 3 years ago

Hi, thanks for your work.

Could you please share the number of parameter of your network? I implemented it and it seems to have more than 34M params?

Thanks!

adityac8 commented 3 years ago

Hi @tuvovan We use the following snippet to calculate the model parameters.

def params_count(model):
    """Computes the number of parameters."""
    return np.sum([p.numel() for p in model.parameters()]).item()

The number of parameters for our MIRNet model are 31.7 Million. In case you want to have a lighter version, you can have a look at #5 for details on adjusting parameters, such as batch_size and n_feat.

Thanks