Có một câu hỏi? Kết nối với cộng đồng tại Diễn đàn Diễn đàn TensorFlow

Module: tf.sparse

Sparse Tensor Representation.

See also `tf.sparse.SparseTensor`.

Classes

`class SparseTensor`: Represents a sparse tensor.

Functions

`add(...)`: Adds two tensors, at least one of each is a `SparseTensor`.

`bincount(...)`: Count the number of times an integer value appears in a tensor.

`concat(...)`: Concatenates a list of `SparseTensor` along the specified dimension. (deprecated arguments)

`cross(...)`: Generates sparse cross from a list of sparse and dense tensors.

`cross_hashed(...)`: Generates hashed sparse cross from a list of sparse and dense tensors.

`expand_dims(...)`: Returns a tensor with an length 1 axis inserted at index `axis`.

`eye(...)`: Creates a two-dimensional sparse tensor with ones along the diagonal.

`fill_empty_rows(...)`: Fills empty rows in the input 2-D `SparseTensor` with a default value.

`from_dense(...)`: Converts a dense tensor into a sparse tensor.

`map_values(...)`: Applies `op` to the `.values` tensor of one or more `SparseTensor`s.

`mask(...)`: Masks elements of `IndexedSlices`.

`maximum(...)`: Returns the element-wise max of two SparseTensors.

`minimum(...)`: Returns the element-wise min of two SparseTensors.

`reduce_max(...)`: Computes `tf.sparse.maximum` of elements across dimensions of a SparseTensor.

`reduce_sum(...)`: Computes `tf.sparse.add` of elements across dimensions of a SparseTensor.

`reorder(...)`: Reorders a `SparseTensor` into the canonical, row-major ordering.

`reset_shape(...)`: Resets the shape of a `SparseTensor` with indices and values unchanged.

`reshape(...)`: Reshapes a `SparseTensor` to represent values in a new dense shape.

`retain(...)`: Retains specified non-empty values within a `SparseTensor`.

`segment_mean(...)`: Computes the mean along sparse segments of a tensor.

`segment_sqrt_n(...)`: Computes the sum along sparse segments of a tensor divided by the sqrt(N).

`segment_sum(...)`: Computes the sum along sparse segments of a tensor.

`slice(...)`: Slice a `SparseTensor` based on the `start` and `size`.

`softmax(...)`: Applies softmax to a batched N-D `SparseTensor`.

`sparse_dense_matmul(...)`: Multiply SparseTensor (or dense Matrix) (of rank 2) "A" by dense matrix

`split(...)`: Split a `SparseTensor` into `num_split` tensors along `axis`.

`to_dense(...)`: Converts a `SparseTensor` into a dense tensor.

`to_indicator(...)`: Converts a `SparseTensor` of ids into a dense bool indicator tensor.

`transpose(...)`: Transposes a `SparseTensor`

[{ "type": "thumb-down", "id": "missingTheInformationINeed", "label":"Missing the information I need" },{ "type": "thumb-down", "id": "tooComplicatedTooManySteps", "label":"Too complicated / too many steps" },{ "type": "thumb-down", "id": "outOfDate", "label":"Out of date" },{ "type": "thumb-down", "id": "samplesCodeIssue", "label":"Samples / code issue" },{ "type": "thumb-down", "id": "otherDown", "label":"Other" }]
[{ "type": "thumb-up", "id": "easyToUnderstand", "label":"Easy to understand" },{ "type": "thumb-up", "id": "solvedMyProblem", "label":"Solved my problem" },{ "type": "thumb-up", "id": "otherUp", "label":"Other" }]