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>
95 lines
2.7 KiB
Python
95 lines
2.7 KiB
Python
# Copyright (C) 2022 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
#
|
|
|
|
from utils import get_path_to_model, get_image, get_path_to_extension_library
|
|
|
|
#! [ie:create_core]
|
|
import numpy as np
|
|
import openvino.inference_engine as ie
|
|
core = ie.IECore()
|
|
#! [ie:create_core]
|
|
|
|
model_path = get_path_to_model(True)
|
|
|
|
#! [ie:read_model]
|
|
network = core.read_network(model_path)
|
|
#! [ie:read_model]
|
|
|
|
#! [ie:compile_model]
|
|
# Load network to the device and create infer requests
|
|
exec_network = core.load_network(network, "CPU", num_requests=4)
|
|
#! [ie:compile_model]
|
|
|
|
#! [ie:create_infer_request]
|
|
# Done in the previous step
|
|
#! [ie:create_infer_request]
|
|
|
|
#! [ie:get_input_tensor]
|
|
infer_request = exec_network.requests[0]
|
|
# Get input blobs mapped to input layers names
|
|
input_blobs = infer_request.input_blobs
|
|
data = input_blobs["data"].buffer
|
|
# Original I64 precision was converted to I32
|
|
assert data.dtype == np.int32
|
|
# Fill the first blob ...
|
|
#! [ie:get_input_tensor]
|
|
|
|
#! [ie:inference]
|
|
results = infer_request.infer()
|
|
#! [ie:inference]
|
|
|
|
input_data = get_image()
|
|
|
|
def process_results(results, frame_id):
|
|
pass
|
|
|
|
#! [ie:start_async_and_wait]
|
|
# Start async inference on a single infer request
|
|
infer_request.async_infer()
|
|
# Wait for 1 milisecond
|
|
infer_request.wait(1)
|
|
# Wait for inference completion
|
|
infer_request.wait()
|
|
|
|
# Demonstrates async pipeline using ExecutableNetwork
|
|
|
|
results = []
|
|
|
|
# Callback to process inference results
|
|
def callback(output_blobs, _):
|
|
# Copy the data from output blobs to numpy array
|
|
results_copy = {out_name: out_blob.buffer[:] for out_name, out_blob in output_blobs.items()}
|
|
results.append(process_results(results_copy))
|
|
|
|
# Setting callback for each infer requests
|
|
for infer_request in exec_network.requests:
|
|
infer_request.set_completion_callback(callback, py_data=infer_request.output_blobs)
|
|
|
|
# Async pipline is managed by ExecutableNetwork
|
|
total_frames = 100
|
|
for _ in range(total_frames):
|
|
# Wait for at least one free request
|
|
exec_network.wait(num_requests=1)
|
|
# Get idle id
|
|
idle_id = exec_network.get_idle_request_id()
|
|
# Start asynchronous inference on idle request
|
|
exec_network.start_async(request_id=idle_id, inputs={"data": input_data})
|
|
# Wait for all requests to complete
|
|
exec_network.wait()
|
|
#! [ie:start_async_and_wait]
|
|
|
|
#! [ie:get_output_tensor]
|
|
# Get output blobs mapped to output layers names
|
|
output_blobs = infer_request.output_blobs
|
|
data = output_blobs["relu"].buffer
|
|
# Original I64 precision was converted to I32
|
|
assert data.dtype == np.int32
|
|
# Process output data
|
|
#! [ie:get_output_tensor]
|
|
|
|
path_to_extension_library = get_path_to_extension_library()
|
|
#! [ie:load_old_extension]
|
|
core.add_extension(path_to_extension_library, "CPU")
|
|
#! [ie:load_old_extension]
|