Katsuya Hyodo PINTO0309

OpenCV ObjDetect Module Face Recognition (SFace) Sample

python generate_aligned_faces.py image.jpg

OpenCVでの処理(リサイズなど)を、簡単にマルチコア化する方法をどなたかご存知でしたら教えて頂けないでしょうか? TBBを使ってスレッドを作る方法は色々見つかったのですが、単にcv::resize()をマルチコア動作で高速化させたいです。

you need to get below files first.

	/*
	* camera.ino - Simple camera example sketch
	* Copyright 2018, 2022 Sony Semiconductor Solutions Corporation
	*
	* This library is free software; you can redistribute it and/or
	* modify it under the terms of the GNU Lesser General Public
	* License as published by the Free Software Foundation; either
	* version 2.1 of the License, or (at your option) any later version.
	*
	* This library is distributed in the hope that it will be useful,

	images = np.zeros((1, 3, 360, 640), dtype=np.float32)
	masks = np.ones((1, 1, 360, 640), dtype=np.float32)

	torch.onnx.export(nnet.model,
	(images, masks),
	"model_float32.onnx",
	export_params=True,
	opset_version=11,
	do_constant_folding=True,
	input_names = ['input_rgb','input_mask'],

	ARG PYTORCH="1.5"
	ARG CUDA="10.1"
	ARG CUDNN="7"

	FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel

	ENV TORCH_CUDA_ARCH_LIST="6.0 6.1 7.0+PTX"
	ENV TORCH_NVCC_FLAGS="-Xfatbin -compress-all"
	ENV CMAKE_PREFIX_PATH="$(dirname $(which conda))/../"

	import tensorflow as tf
	import numpy as np
	import mrcnn.model as modellib # https://github.com/matterport/Mask_RCNN/
	from mrcnn.config import Config
	import keras.backend as keras

	PATH_TO_SAVE_FROZEN_PB ="./"
	FROZEN_NAME ="saved_model.pb"