docs fixing

Author: dfalbel

R/install.R

@@ -68,7 +68,7 @@
 #' desired backend) as described on the [Keras website](https://keras.io/#installation)
 #' and the Keras R package will find and use that version. 
 #' 
-#' See the documentation on [custom installations](https://tensorflow.rstudio.com/installation.html#custom-installation)
+#' See the documentation on [custom installations](https://tensorflow.rstudio.com/installation/custom/)
 #' for additional information on how version of Keras and TensorFlow are located
 #' by the Keras package.
 #'

man/get_layer.Rd

@@ -75,7 +75,7 @@ model %>%
 There are many `layers` available with some common constructor
 parameters:
 
-  - `activation`: Set the [activation function](https://tensorflow.rstudio.com/keras/reference/#section-activation-layers) for the layer. By default, no activation is applied.
+  - `activation`: Set the [activation function](https://tensorflow.rstudio.com/reference/keras/#section-activation-layers) for the layer. By default, no activation is applied.
   - `kernel_initializer` and `bias_initializer`: The initialization
     schemes that create the layer’s weights (kernel and bias). This defaults to the
     [`Glorot uniform`](https://tensorflow.rstudio.com/keras/reference/initializer_glorot_uniform.html) initializer.

man/install_keras.Rd

@@ -57,7 +57,7 @@ install.packages("keras")
 install_keras()
 ```
 
-This will provide you with default CPU-based installations of Keras and TensorFlow. If you want a more customized installation, e.g. if you want to take advantage of NVIDIA GPUs, see the documentation for `install_keras()` and the [installation](/installation/) section.
+This will provide you with default CPU-based installations of Keras and TensorFlow. If you want a more customized installation, e.g. if you want to take advantage of NVIDIA GPUs, see the documentation for `install_keras()` and the [installation](https://tensorflow.rstudio.com/installation/) section.
 
 ## MNIST Example