I would like to perform Softmax Regression for image classification using Fastai V2, I do not want to use a pretrained model.
Is there a way to do it? Could you please show me an example?
Thank you,
Henry
I would like to perform Softmax Regression for image classification using Fastai V2, I do not want to use a pretrained model.
Is there a way to do it? Could you please show me an example?
Thank you,
Henry
This is the solution:
class SoftMax(nn.Module):
def init(self, in_size, out_size):
super(SoftMax,self).init()
self.linear = nn.Linear(in_size, out_size)
def forward(self,x):
x = x.view(-1, in_size)
out = F.softmax(self.linear(x))
return out
soft_max_model = SoftMax(in_size,out_size)