Optimizer

Utility functions for FastAI optimizers in Pytorch models.

Some utility functions for training Pytorch models with FastAI fine tuning method. The code is from this repository.

---

source

params

 params (m)

Return all parameters of m (Pytorch model).

---

source

convert_params

 convert_params (o:list)

*Converts o into Pytorch-compatable param groups o should be a set of layer-groups that should be split in the optimizer Example:

def splitter(m): return convert_params([[m.a], [m.b]])

Where m is a model defined as: python class RegModel(Module): def __init__(self): self.a,self.b = nn.Parameter(torch.randn(1)),nn.Parameter(torch.randn(1)) def forward(self, x): return x*self.a + self.b*

In the FastAI library is largely used transfer learning with layer-group learning rate freezing. The convert_params function returns a list of parameters for specific layers in a model that allows discriminative learning rates.

---

source

smp_splitter

 smp_splitter (model)

---

source

opt_func

 opt_func (params, torch_opt, *args, **kwargs)

Pytorch Optimizer for fastai Learner.