2bf8d910f6
* [Docs][PyOV] update python snippets * first snippet * Fix samples debug * Fix linter * part1 * Fix speech sample * update model state snippet * add serialize * add temp dir * CPU snippets update (#134) * snippets CPU 1/6 * snippets CPU 2/6 * snippets CPU 3/6 * snippets CPU 4/6 * snippets CPU 5/6 * snippets CPU 6/6 * make module TODO: REMEMBER ABOUT EXPORTING PYTONPATH ON CIs ETC * Add static model creation in snippets for CPU * export_comp_model done * leftovers * apply comments * apply comments -- properties * small fixes * rempve debug info * return IENetwork instead of Function * apply comments * revert precision change in common snippets * update opset * [PyOV] Edit docs for the rest of plugins (#136) * modify main.py * GNA snippets * GPU snippets * AUTO snippets * MULTI snippets * HETERO snippets * Added properties * update gna * more samples * Update docs/OV_Runtime_UG/model_state_intro.md * Update docs/OV_Runtime_UG/model_state_intro.md * attempt1 fix ci * new approach to test * temporary remove some files from run * revert cmake changes * fix ci * fix snippet * fix py_exclusive snippet * fix preprocessing snippet * clean-up main * remove numpy installation in gha * check for GPU * add logger * iexclude main * main update * temp * Temp2 * Temp2 * temp * Revert temp * add property execution devices * hide output from samples --------- Co-authored-by: p-wysocki <przemyslaw.wysocki@intel.com> Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com> Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
75 lines
2.5 KiB
Python
75 lines
2.5 KiB
Python
# Copyright (C) 2018-2023 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
import numpy as np
|
|
import openvino as ov
|
|
import openvino.runtime.opset12 as ops
|
|
|
|
INPUT_SIZE = 1_000_000 # Use bigger values if necessary, i.e.: 300_000_000
|
|
|
|
input_0 = ops.parameter([INPUT_SIZE], name="input_0")
|
|
input_1 = ops.parameter([INPUT_SIZE], name="input_1")
|
|
add_inputs = ops.add(input_0, input_1)
|
|
res = ops.reduce_sum(add_inputs, reduction_axes=0, name="reduced")
|
|
model = ov.Model(res, [input_0, input_1], name="my_model")
|
|
model.outputs[0].tensor.set_names({"reduced_result"}) # Add name for Output
|
|
|
|
core = ov.Core()
|
|
compiled_model = core.compile_model(model, device_name="CPU")
|
|
|
|
data_0 = np.array([0.1] * INPUT_SIZE, dtype=np.float32)
|
|
data_1 = np.array([-0.1] * INPUT_SIZE, dtype=np.float32)
|
|
|
|
data_2 = np.array([0.2] * INPUT_SIZE, dtype=np.float32)
|
|
data_3 = np.array([-0.2] * INPUT_SIZE, dtype=np.float32)
|
|
|
|
#! [direct_inference]
|
|
# Calling CompiledModel creates and saves InferRequest object
|
|
results_0 = compiled_model({"input_0": data_0, "input_1": data_1})
|
|
# Second call reuses previously created InferRequest object
|
|
results_1 = compiled_model({"input_0": data_2, "input_1": data_3})
|
|
#! [direct_inference]
|
|
|
|
request = compiled_model.create_infer_request()
|
|
|
|
#! [shared_memory_inference]
|
|
# Data can be shared only on inputs
|
|
_ = compiled_model({"input_0": data_0, "input_1": data_1}, share_inputs=True)
|
|
_ = request.infer({"input_0": data_0, "input_1": data_1}, share_inputs=True)
|
|
# Data can be shared only on outputs
|
|
_ = request.infer({"input_0": data_0, "input_1": data_1}, share_outputs=True)
|
|
# Or both flags can be combined to achieve desired behavior
|
|
_ = compiled_model({"input_0": data_0, "input_1": data_1}, share_inputs=False, share_outputs=True)
|
|
#! [shared_memory_inference]
|
|
|
|
time_in_sec = 2.0
|
|
|
|
#! [hiding_latency]
|
|
import time
|
|
|
|
# Long running function
|
|
def run(time_in_sec):
|
|
time.sleep(time_in_sec)
|
|
|
|
# No latency hiding
|
|
results = request.infer({"input_0": data_0, "input_1": data_1})[0]
|
|
run(time_in_sec)
|
|
|
|
# Hiding latency
|
|
request.start_async({"input_0": data_0, "input_1": data_1})
|
|
run(time_in_sec)
|
|
request.wait()
|
|
results = request.get_output_tensor(0).data # Gather data from InferRequest
|
|
#! [hiding_latency]
|
|
|
|
#! [no_return_inference]
|
|
# Standard approach
|
|
results = request.infer({"input_0": data_0, "input_1": data_1})[0]
|
|
|
|
# "Postponed Return" approach
|
|
request.start_async({"input_0": data_0, "input_1": data_1})
|
|
request.wait()
|
|
results = request.get_output_tensor(0).data # Gather data "on demand" from InferRequest
|
|
#! [no_return_inference]
|
|
|