Dynamic U-Net¶
This module builds a dynamic U-Net from any backbone pretrained on ImageNet, automatically inferring the intermediate sizes.
from fastai.gen_doc.nbdoc import *
from fastai.vision.models.unet import *
This is the original U-Net. The difference here is that the left part is a pretrained model.
show_doc(DynamicUnet)
class DynamicUnet[source][test]
DynamicUnet(encoder:Module,n_classes:int,blur:bool=*False,blur_final=True,self_attention:bool=False,y_range:OptRange=None,last_cross:bool=True,bottle:bool=False, ***kwargs**) ::SequentialEx
No tests found for DynamicUnet. To contribute a test please refer to this guide and this discussion.
Create a U-Net from a given architecture.
This U-Net will sit on top of an encoder (that can be a pretrained model) and with a final output of n_classes. During the initialization, it uses Hooks to determine the intermediate features sizes by passing a dummy input through the model and create the upward path automatically.
blur is used to avoid checkerboard artifacts at each layer, blur_final is specific to the last layer. self_attention determines if we use a self attention layer at the third block before the end. If y_range is passed, the last activations go through a sigmoid rescaled to that range. last_cross determines if we use a cross-connection with the direct input of the model, and in this case bottle flags if we use a bottleneck or not for that skip connection.
show_doc(UnetBlock)
class UnetBlock[source][test]
UnetBlock(up_in_c:int,x_in_c:int,hook:Hook,final_div:bool=*True,blur:bool=False,leaky:float=None,self_attention:bool=False, ***kwargs**) ::Module
No tests found for UnetBlock. To contribute a test please refer to this guide and this discussion.
A quasi-UNet block, using PixelShuffle_ICNR upsampling.
This block receives the output of the last block to be upsampled (size up_in_c) and the activations features from an intermediate layer of the encoder (size x_in_c, this is the lateral connection). The hook is set to this intermediate layer to store the output needed for this block. final_div determines if we divide the number of features by 2 with the upsampling, blur is to avoid checkerboard artifacts. If leaky is set, use a leaky ReLU with a slope equals to that parameter instead of a ReLU, and self_attention determines if we use a self-attention layer. kwargs are passed to conv_layer.
Undocumented Methods - Methods moved below this line will intentionally be hidden¶
show_doc(UnetBlock.forward)
forward[source][test]
forward(up_in:Tensor) →Tensor
No tests found for forward. To contribute a test please refer to this guide and this discussion.
Defines the computation performed at every call. Should be overridden by all subclasses.
.. note::
Although the recipe for forward pass needs to be defined within
this function, one should call the :class:Module instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.