LinearMemoryPlanner

class LinearMemoryPlanner : public tflite::MicroMemoryPlanner

The simplest possible memory planner that just lays out all buffers at increasing offsets without trying to reuse memory.

tflite::LinearMemoryPlanner::LinearMemoryPlanner()

tflite::LinearMemoryPlanner::~LinearMemoryPlanner()

TfLiteStatus tflite::LinearMemoryPlanner::AddBuffer(int size, int first_time_used, int last_time_used)

Pass information about a buffer’s size and lifetime to the layout algorithm. The order this is called implicitly assigns an index to the result, so the buffer information that’s passed into the N-th call of this method will be used as the buffer_index argument to GetOffsetForBuffer().

Parameters

Parameters of AddBuffer
Name	Type	Default
`size`	`int`	Required
`first_time_used`	`int`	Required
`last_time_used`	`int`	Required

size_t tflite::LinearMemoryPlanner::GetMaximumMemorySize()

The largest contiguous block of memory that’s needed to hold the layout.

int tflite::LinearMemoryPlanner::GetBufferCount()

How many buffers have been added to the planner.

TfLiteStatus tflite::LinearMemoryPlanner::GetOffsetForBuffer(int buffer_index, int *offset)

Calculated layout offset for the N-th buffer added to the planner.

Parameters

Parameters of GetOffsetForBuffer
Name	Type	Default	Description
`buffer_index`	`int`	Required
`offset`	`int *`	Required

bool tflite::LinearMemoryPlanner::preserves_all_tensors() const

Returns True because the LinearMemoryPlanner preserves all tensors after invocation.