Rebase errors

src/convnets/convnext.jl

@@ -7,7 +7,7 @@ Creates a single block of ConvNeXt.
 # Arguments
 
   - `planes`: number of input channels.
-  - `drop_path_rate`: Stochastic depth rate.
+  - `stochastic_depth_prob`: Stochastic depth probability.
   - `layerscale_init`: Initial value for [`Metalhead.LayerScale`](@ref)
 """
 function convnextblock(planes::Integer, stochastic_depth_prob = 0.0,
@@ -33,13 +33,8 @@ Creates the layers for a ConvNeXt model.
 
   - `depths`: list with configuration for depth of each block
   - `planes`: list with configuration for number of output channels in each block
-<<<<<<< HEAD
   - `stochastic_depth_prob`: Stochastic depth probability.
   - `layerscale_init`: Initial value for [`LayerScale`](@ref)
-=======
-  - `drop_path_rate`: Stochastic depth rate.
-  - `layerscale_init`: Initial value for [`Metalhead.LayerScale`](@ref)
->>>>>>> 5ac81ce (Use `@autodocs` and fix references)
     ([reference](https://arxiv.org/abs/2103.17239))
   - `inchannels`: number of input channels.
   - `nclasses`: number of output classes
@@ -101,13 +96,10 @@ Creates a ConvNeXt model.
   - `inchannels`: number of input channels
   - `nclasses`: number of output classes
 
-<<<<<<< HEAD
 !!! warning
     
     `ConvNeXt` does not currently support pretrained weights.
 
-=======
->>>>>>> 5ac81ce (Use `@autodocs` and fix references)
 See also [`Metalhead.convnext`](@ref).
 """
 struct ConvNeXt

src/convnets/resnets/core.jl

@@ -66,11 +66,7 @@ used to build the block for the model, see [`Metalhead.bottleneck_builder`](@ref
   - `revnorm`: set to `true` to place the normalisation layer before the convolution
   - `drop_block`: the drop block layer
   - `drop_path`: the drop path layer
-<<<<<<< HEAD
   - `attn_fn`: the attention function to use. See [`squeeze_excite`](@ref) for an example.
-=======
-  - `attn_fn`: the attention function to use. See [`Metalhead.squeeze_excite`](@ref) for an example.
->>>>>>> 5ac81ce (Use `@autodocs` and fix references)
 """
 function bottleneck(inplanes::Integer, planes::Integer; stride::Integer,
                     cardinality::Integer = 1, base_width::Integer = 64,
@@ -235,11 +231,7 @@ const RESNET_SHORTCUTS = Dict(:A => (downsample_identity, downsample_identity),
     resnet_stem(; stem_type = :default, inchannels::Integer = 3, replace_stem_pool = false,
                   norm_layer = BatchNorm, activation = relu)
 
-<<<<<<< HEAD
 Builds a stem to be used in a ResNet model. See the `stem` argument of [`resnet`](@ref) for details
-=======
-Builds a stem to be used in a ResNet model. See the `stem` argument of [`Metalhead.resnet`](@ref) for details
->>>>>>> 5ac81ce (Use `@autodocs` and fix references)
 on how to use this function.
 
 # Arguments

src/convnets/resnets/resnet.jl

@@ -48,11 +48,7 @@ The number of channels in outer 1x1 convolutions is the same.
   - `inchannels`: The number of input channels.
   - `nclasses`: The number of output classes
 
-<<<<<<< HEAD
 Advanced users who want more configuration options will be better served by using [`resnet`](@ref).
-=======
-Advanced users who want more configuration options will be better served by using [`Metalhead.resnet`](@ref).
->>>>>>> 5ac81ce (Use `@autodocs` and fix references)
 """
 struct WideResNet
     layers::Any

src/convnets/resnets/seresnet.jl

@@ -58,11 +58,7 @@ Creates a SEResNeXt model with the specified depth, cardinality, and base width.
     
     `SEResNeXt` does not currently support pretrained weights.
 
-<<<<<<< HEAD
 Advanced users who want more configuration options will be better served by using [`resnet`](@ref).
-=======
-Advanced users who want more configuration options will be better served by using [`Metalhead.resnet`](@ref).
->>>>>>> 5ac81ce (Use `@autodocs` and fix references)
 """
 struct SEResNeXt
     layers::Any