tf.conv2d_backprop_input_v2

Computes the gradients of convolution with respect to the input.

tf.conv2d_backprop_input_v2(
    input: Annotated[Any, TV_Conv2DBackpropInputV2_T],
    filter: Annotated[Any, TV_Conv2DBackpropInputV2_T],
    out_backprop: Annotated[Any, TV_Conv2DBackpropInputV2_T],
    strides,
    padding: str,
    use_cudnn_on_gpu: bool = True,
    explicit_paddings=[],
    data_format: str = 'NHWC',
    dilations=[1, 1, 1, 1],
    name=None
) -> Annotated[Any, TV_Conv2DBackpropInputV2_T]

input A Tensor. Must be one of the following types: half, bfloat16, float32, float64, int32. 4-D with shape [batch, in_height, in_width, in_channels]. Only shape of tensor is used. filter A Tensor. Must have the same type as input. 4-D with shape [filter_height, filter_width, in_channels, out_channels]. out_backprop A Tensor. Must have the same type as input. 4-D with shape [batch, out_height, out_width, out_channels]. Gradients w.r.t. the output of the convolution. strides A list of ints. The stride of the sliding window for each dimension of the input of the convolution. Must be in the same order as the dimension specified with format. padding A string from: "SAME", "VALID", "EXPLICIT". The type of padding algorithm to use. use_cudnn_on_gpu An optional bool. Defaults to True. explicit_paddings An optional list of ints. Defaults to []. If padding is "EXPLICIT", the list of explicit padding amounts. For the ith dimension, the amount of padding inserted before and after the dimension is explicit_paddings[2 * i] and explicit_paddings[2 * i + 1], respectively. If padding is not "EXPLICIT", explicit_paddings must be empty. data_format An optional string from: "NHWC", "NCHW". Defaults to "NHWC". Specify the data format of the input and output data. With the default format "NHWC", the data is stored in the order of: [batch, in_height, in_width, in_channels]. Alternatively, the format could be "NCHW", the data storage order of: [batch, in_channels, in_height, in_width]. dilations An optional list of ints. Defaults to [1, 1, 1, 1]. 1-D tensor of length 4. The dilation factor for each dimension of input. If set to k > 1, there will be k-1 skipped cells between each filter element on that dimension. The dimension order is determined by the value of data_format, see above for details. Dilations in the batch and depth dimensions must be 1. name A name for the operation (optional).