Python Reference
shape
- class migraphx.shape(type, lens, strides=None)
Describes the shape of a tensor. This includes size, layout, and data type/
- migraphx.type()
An integer that represents the type
- Return type
int
- migraphx.lens()
A list of the lengths of the shape
- Return type
list[int]
- migraphx.strides()
A list of the strides of the shape
- Return type
list[int]
- migraphx.elements()
The number of elements in the shape
- Return type
int
- migraphx.bytes()
The number of bytes the shape uses
- Return type
int
- migraphx.type_size()
The number of bytes one element uses
- Return type
int
- migraphx.packed()
Returns true if the shape is packed.
- Return type
bool
- migraphx.transposed()
Returns true if the shape is transposed.
- Return type
bool
- migraphx.broadcasted()
Returns true if the shape is broadcasted.
- Return type
bool
- migraphx.standard()
Returns true if the shape is a standard shape. That is, the shape is both packed and not transposed.
- Return type
bool
- migraphx.scalar()
Returns true if all strides are equal to 0 (scalar tensor).
- Return type
bool
argument
- class migraphx.argument(data)
Construct an argument from a python buffer. This can include numpy arrays.
- migraphx.tolist()
Convert the elements of the argument to a python list.
- Return type
list
target
- class migraphx.target
This represents the compiliation target.
program
- class migraphx.program
Represents the computation graph to be compiled and run.
- migraphx.get_parameter_shapes()
Get the shapes of all the input parameters in the program.
- Return type
dict[str, shape]
- migraphx.compile(t, offload_copy=True, fast_math=True)
Compiles the program for the target and optimizes it.
- Parameters
t (target) – This is the target to compile the program for.
offload_copy (bool) – For targets with offloaded memory(such as the gpu), this will insert instructions during compilation to copy the input parameters to the offloaded memory and to copy the final result from the offloaded memory back to main memory.
fast_math (bool) – Optimize math functions to use faster approximate versions. There may be slight accuracy degredation when enabled.
- migraphx.run(params)
Run the program.
- migraphx.quantize_fp16(prog, ins_names=['all'])
Quantize the program to use fp16.
- Parameters
prog (program) – Program to quantize.
ins_names (list[str]) – List of instructions to quantize.
- migraphx.quantize_int8(prog, t, calibration=[], ins_names=['dot', 'convolution'])
Quantize the program to use int8.
parse_onnx
- migraphx.parse_onnx(filename, default_dim_value=1, map_input_dims={}, skip_unknown_operators=false, print_program_on_error=false)
Load and parse an onnx file.
- Parameters
filename (str) – Path to file.
default_dim_value (str) – default batch size to use (if not specified in onnx file).
map_input_dims (str) – Explicitly specify the dims of an input.
skip_unknown_operators (str) – Continue parsing onnx file if an unknown operator is found.
print_program_on_error (str) – Print program if an error occurs.
- Return type