Derived-types/Convolution-layers/conv2d_layer_type.md

@@ -19,7 +19,7 @@ This layer creates a convolution kernel that is convolved with the layer input t
 
 #### Arguments
 
-* **input_shape**: The shape of the input data for one sample.
+* **input_shape**: The shape of the input data for one sample. This is required only if this layer is the first (non-input) layer of the network.
 * **num_filters**: Integer. The number of output filters in the convolution (i.e. the number of output channels).
 * **kernel_size**: An integer or 1D-array of 2 integers. Specifies the width and depth of the convolution kernel. Providing a scalar integer specifies the same value for all dimensions. `Default = 3`.
 * **stride**: An integer or 1D-array of 2 integers. Specifies the strides of the convolution along each spatial dimension. Providing a scalar integer specifies the same value for all dimensions. `Default = 1`.