Prepare the dataframe for display

Cleans up any saved models or loaded models from memory.

\brief clear a single build mode flag. clears the builder mode flag from the enabled flags. \see setFlags()

\brief Combine input timing cache into local instance. This function allows combining entries in the input timing cache to local cache object. \para

Convert in-memory Keras model into ONNX format. Works directly with CreateAssetsFolder object path. Args: keras_model (tf.keras.Model

Parse the ONNX graph and create the corresponding TensorRT network definition. :param onnx_path: The path to the ONNX graph to load.

\brief Destroy this object. \deprecated Deprecated in TensorRT 8.0. Superseded by `delete`. \warning Calling destroy on a managed pointer will resul

Enable clip stage

Exports an onnx-graphsurgeon Graph to an ONNX model. Args: graph (Graph): The graph to export do_type_check (bool): Whether

Create descriptor from yaml str

Generates the roi input name for the Resize node.

Gets a command-line argument if it exists, otherwise returns a default value. Args: args: The command-line arguments. attr (

\brief Get the LRN alpha value. \see setAlpha()

\brief Get the LRN beta value. \see setBeta()

If isConstant(), returns value of the constant. If !isConstant(), return std::numeric_limits<int32_t>::min().

\brief Get maximum of dynamic range. \return Maximum of dynamic range, or quiet NaN if range was not set.

\brief Get minimum of dynamic range. \return Minimum of dynamic range, or quiet NaN if range was not set.

\brief Returns true if the build mode flag is set \see getFlags() \return True if flag is set, false if unset.

\brief Get the multi-dimension kernel size of the convolution. \see setKernelSizeNd()

< set the Max Batch Size

\brief Get names of missing weights. For example, if some Weights have been set, but the engine was optimized in a way that combines weights, any uns

\brief Return the number of DLA engines available to this builder.

\brief Get the number of groups of the convolution. \see setNbGroups()

\brief Get the number of output maps for the convolution. \see setNbOutputMaps()

\brief Get the number of outputs of a layer.

\brief Get the padding for pooling. Default: 0 \see setPadding() \deprecated Superseded by getPaddingNd. Deprecated prior to TensorRT 8.0 and will

\brief Get the padding mode. Default: kEXPLICIT_ROUND_DOWN \see setPaddingMode()

\brief Get the multi-dimension padding for pooling. If the padding is asymmetric, the pre-padding is returned. \see setPaddingNd()

\brief Get the reshaped dimensions. \return The reshaped dimensions. If a second input is present and non-null, or setReshapeDimensions has not yet

\brief Get the scale value. \see setScale()

\brief Copies resize scales to scales[0, ..., nbScales-1], where nbScales is the number of scales that were set. \param size The number of scales to

\brief Get the shift value. \see setShift()

\brief Get the multi-dimension stride for pooling. \see setStrideNd()

\brief Get tactic sources. Get the tactic sources currently set in the engine build configuration. \see setTacticSources() \return tactic sources

\brief Return the number of bytes per component of an element, or -1 if the provided name does not map to an input or output tensor. The vector compo

\brief Determine the required data type for a buffer from its tensor name. \param tensorName The name of an input or output tensor. \return The type

\brief Return the human readable description of the tensor format, or empty string if the provided name does not map to an input or output tensor. Th

\brief Return the strides of the buffer for the given tensor name. The strides are in units of elements, not components or bytes. For example, for Te

\brief Get names of all tensors that have refittable dynamic ranges. \param size The number of items that can be safely written to a non-null tensorN