tf.raw_ops.Conv3DBackpropInputV2 | TensorFlow v2.16.1 (original) (raw)

tf.raw_ops.Conv3DBackpropInputV2

Stay organized with collections Save and categorize content based on your preferences.

Computes the gradients of 3-D convolution with respect to the input.

View aliases

Compat aliases for migration

tf.compat.v1.raw_ops.Conv3DBackpropInputV2

tf.raw_ops.Conv3DBackpropInputV2(
    input_sizes,
    filter,
    out_backprop,
    strides,
    padding,
    data_format='NDHWC',
    dilations=[1, 1, 1, 1, 1],
    name=None
)

Args
input_sizes	A Tensor. Must be one of the following types: int32, int64. An integer vector representing the tensor shape of input, where input is a 5-D[batch, depth, rows, cols, in_channels] tensor.
filter	A Tensor. Must be one of the following types: half, bfloat16, float32, float64. Shape [depth, rows, cols, in_channels, out_channels].in_channels must match between input and filter.
out_backprop	A Tensor. Must have the same type as filter. Backprop signal of shape [batch, out_depth, out_rows, out_cols, out_channels].
strides	A list of ints that has length >= 5. 1-D tensor of length 5. The stride of the sliding window for each dimension of input. Must have strides[0] = strides[4] = 1.
padding	A string from: "SAME", "VALID". The type of padding algorithm to use.
data_format	An optional string from: "NDHWC", "NCDHW". Defaults to "NDHWC". The data format of the input and output data. With the default format "NDHWC", the data is stored in the order of: [batch, in_depth, in_height, in_width, in_channels]. Alternatively, the format could be "NCDHW", the data storage order is: [batch, in_channels, in_depth, in_height, in_width].
dilations	An optional list of ints. Defaults to [1, 1, 1, 1, 1]. 1-D tensor of length 5. The dilation factor for each dimension ofinput. 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).

Returns
A Tensor. Has the same type as filter.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.