dot multiply Args: a (CTensor): 2d input tensor. b (CTensor): 2d input tensor. Returns: C

Gets the number of failed tests.

Verbosity of the time profiling function: verbosity == 0 (default) -> no logging verbosity == 1 -> display forward and backward propagation time verbo

Disabled by default.

Constructs and returns the message for an equality assertion (e.g. ASSERT_EQ, EXPECT_STREQ, etc) failure. The first four parameters are the expressio

Returns an indented copy of stderr output for a death test. This makes distinguishing death test output lines from regular log lines much easier.

Returns the message describing the last system error in errno.

Parses the environment variable var as an Int32. If it is unset, returns default_val. If it is not an Int32, prints an error and aborts.

Multiply column 'v' and each column of matrix M; write results into 'out'

Reads and returns the string environment variable corresponding to the given flag; if it's not set, returns default_value.

shallow copy. Returns: a new Tensor which shares the underlying data memory (shallow copy).

Args: t (Tensor): input Tensor Returns: a new Tensor whose element y = abs(x), x is an element of t

Returns: a new Tensor which does deep copy of this tensor

Compile and initialize the model This function will automatically derive the shape of parameters in each sublayer based on the shape

Copy data from other Tensor instance. Args: t (Tensor): source Tensor.

Apply random enhancement for Color,Contrast,Brightness,Sharpness. Args: scale(float): enhancement degree is from [1-scale, 1+scal

Absolute value. See also:** Documentation for [std::fabs](https://en.cppreference.com/w/cpp/numeric/math/fabs). \param arg operand \return absolute va

Nearest integer not greater than half value. See also:** Documentation for [std::floor](https://en.cppreference.com/w/cpp/numeric/math/floor). \param

Performs all reduce of the tensors after fusing and converting them to FP16. Args: tensor(List of Tensors): a list of tensors

:param args: :param loapi: Local score API, records all scored arch, 101 use it to detect which arch is scored. :return:

Provides access to the event listener list.

Returns the working directory when the first TEST() or TEST_F() was executed.

Repeat data of a tensor Args: repeats(int or a sequence): the number that the tensor need to repeat for axis (int):th

Nearest integer. See also:** Documentation for [std::round](https://en.cppreference.com/w/cpp/numeric/math/round). \param arg half to round \return ne

the number of initial iteration that is skipped for time profiling

Move the tensor data onto the default host CppCPU device.

Set the model in evaluation mode. Args: mode(bool): when mode is True, this model will enter training mode

To transpose the tensor Args: t: input tensor axes: axes to transpose Returns: the transposed tensor

Returns true iff the test failed.

Formats a countable noun. Depending on its quantity, either the singular form or the plural form is used. e.g. FormatCountableNoun(1, "formula", "fo

Formats the count of tests.

DEPRECATED use l2()

* Push an element into the queue. Blocking operation. * @return true if success; */