A walk with fastai2 - Vision - Study Group and Online Lectures Megathread

muellerzr · February 21, 2020, 11:07pm

dls.c is made if we pass our dataloaders to cnn_learner. It will read this to figure out how many outputs we want in our head

It gets split between the two, so it turns into 512 (they both run at once). Another thing to explore for this is how create_head uses the input filters

And here:

github.com

fastai/fastai2/blob/master/fastai2/vision/learner.py#L101


      
          
          # Cell
          from ..callback.hook import num_features_model
          
          # Cell
          @delegates(create_head)
          def create_cnn_model(arch, n_out, cut=None, pretrained=True, n_in=3, init=nn.init.kaiming_normal_, custom_head=None,
                               concat_pool=True, **kwargs):
              "Create custom convnet architecture using `arch`, `n_in` and `n_out`"
              body = create_body(arch, n_in, pretrained, cut)
              if custom_head is None:
                  nf = num_features_model(nn.Sequential(*body.children())) * (2 if concat_pool else 1)
                  head = create_head(nf, n_out, concat_pool=concat_pool, **kwargs)
              else: head = custom_head
              model = nn.Sequential(body, head)
              if init is not None: apply_init(model[1], init)
              return model
          
          # Cell
          @delegates(create_cnn_model)
          def cnn_config(**kwargs):