Closed tuvovan closed 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
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!