拒绝光照影响，一文教你在地平线旭日派X3上如何使用resnet18搭建自己的深度学习巡线小车

获取训练的代码请关注这个佬的文章,大佬,我这里只说怎么转模型，并且在旭日派X3部署

1. 在ubuntu虚拟机中将onnx模型转为bin模型

第一步将自己的resnet的onnx模型拖入虚拟机中
获取地平线官方的转换例程

选择分类中的resnet18

当前目录的结构就是这样的

修改01_check_X3.sh脚本

不过多解释，就按照我这个修改就行，具体可以到地平线社区查找

之后执行该脚本

修改02_preprocess.sh，可以使用训练时的图片

修改resnet18_config_X3.yaml文件

修改模型的路径，以及转换后模型的名称，归一化的类型等

# Copyright (c) 2020 Horizon Robotics.All Rights Reserved.
#
# The material in this file is confidential and contains trade secrets
# of Horizon Robotics Inc. This is proprietary information owned by
# Horizon Robotics Inc. No part of this work may be disclosed,
# reproduced, copied, transmitted, or used in any way for any purpose,
# without the express written permission of Horizon Robotics Inc.# 模型转化相关的参数
# ------------------------------------
# model conversion related parameters
model_parameters:# Caffe浮点网络数据模型文件# ---------------------------------------------------------------------------------------------# the model file of floating-point Caffe neural network dataonnx_model: 'model_best_03.onnx'# Caffe网络描述文件# -----------------------------------------------------------------------------------------------# the file describes the structure of Caffe neural network# prototxt: '../../../01_common/model_zoo/mapper/classification/resnet18/resnet18_deploy.prototxt'# 适用BPU架构# ---------------------------------------------------------------------------------------# the applicable BPU architecturemarch: "bernoulli2"# 指定模型转换过程中是否输出各层的中间结果，如果为True，则输出所有层的中间输出结果，# ---------------------------------------------------------------------------------------# specifies whether or not to dump the intermediate results of all layers in conversion# if set to True, then the intermediate results of all layers shall be dumpedlayer_out_dump: False# 模型转换输出的结果的存放目录# ---------------------------------------------------------------------------------------# the directory in which model conversion results are storedworking_dir: 'model_output'# 模型转换输出的用于上板执行的模型文件的名称前缀# ---------------------------------------------------------------------------------------# model conversion generated name prefix of those model files used for dev board executionoutput_model_file_prefix: 'resnet18_224x224_nv12'# 模型输入相关参数, 若输入多个节点, 则应使用';'进行分隔, 使用默认缺省设置则写None
# -------------------------------------------------------------------------
# model input related parameters,
# please use ";" to seperate when inputting multiple nodes,
# please use None for default setting
input_parameters:# (选填) 模型输入的节点名称, 此名称应与模型文件中的名称一致, 否则会报错, 不填则会使用模型文件中的节点名称# -------------------------------------------------------------------------------------------------# (Optional) node name of model input,# it shall be the same as the name of model file, otherwise an error will be reported,# the node name of model file will be used when left blankinput_name: ""# 网络实际执行时，输入给网络的数据格式，包括 nv12/rgb/bgr/yuv444/gray/featuremap,# ------------------------------------------------------------------------------------------# the data formats to be passed into neural network when actually performing neural network# available options: nv12/rgb/bgr/yuv444/gray/featuremap,input_type_rt: 'nv12'# 网络实际执行时输入的数据排布, 可选值为 NHWC/NCHW# 若input_type_rt配置为nv12，则此处参数不需要配置# ------------------------------------------------------------------# the data layout formats to be passed into neural network when actually performing neural network, available options: NHWC/NCHW# If input_type_rt is configured as nv12, then this parameter does not need to be configuredinput_layout_rt: ''# 网络训练时输入的数据格式，可选的值为rgb/bgr/gray/featuremap/yuv444# ---------------------------------------------------------------------# the data formats in network training# available options: rgb/bgr/gray/featuremap/yuv444input_type_train: 'rgb'# 网络训练时输入的数据排布, 可选值为 NHWC/NCHW# ---------------------------------------------------------------------# the data layout in network training, available options: NHWC/NCHWinput_layout_train: 'NCHW'# (选填) 模型网络的输入大小, 以'x'分隔, 不填则会使用模型文件中的网络输入大小，否则会覆盖模型文件中输入大小# -------------------------------------------------------------------------------------------# (Optional)the input size of model network, seperated by 'x'# note that the network input size of model file will be used if left blank# otherwise it will overwrite the input size of model fileinput_shape: ''# 网络实际执行时，输入给网络的batch_size, 默认值为1# ---------------------------------------------------------------------# the data batch_size to be passed into neural network when actually performing neural network, default value: 1#input_batch: 1# 网络输入的预处理方法，主要有以下几种：# no_preprocess 不做任何操作# data_mean 减去通道均值mean_value# data_scale 对图像像素乘以data_scale系数# data_mean_and_scale 减去通道均值后再乘以scale系数# -------------------------------------------------------------------------------------------# preprocessing methods of network input, available options:# 'no_preprocess' indicates that no preprocess will be made # 'data_mean' indicates that to minus the channel mean, i.e. mean_value# 'data_scale' indicates that image pixels to multiply data_scale ratio# 'data_mean_and_scale' indicates that to multiply scale ratio after channel mean is minusednorm_type: 'data_mean_and_scale'# 图像减去的均值, 如果是通道均值，value之间必须用空格分隔# --------------------------------------------------------------------------# the mean value minused by image# note that values must be seperated by space if channel mean value is usedmean_value: '123.675 116.28 103.53'# 图像预处理缩放比例，如果是通道缩放比例，value之间必须用空格分隔# ---------------------------------------------------------------------------# scale value of image preprocess# note that values must be seperated by space if channel scale value is usedscale_value:  '0.0171248 0.017507 0.0174292'# 模型量化相关参数
# -----------------------------
# model calibration parameters
calibration_parameters:# 模型量化的参考图像的存放目录，图片格式支持Jpeg、Bmp等格式，输入的图片# 应该是使用的典型场景，一般是从测试集中选择20~100张图片，另外输入# 的图片要覆盖典型场景，不要是偏僻场景，如过曝光、饱和、模糊、纯黑、纯白等图片# 若有多个输入节点, 则应使用';'进行分隔# -----------------------------------------------------------------------# the directory where reference images of model quantization are stored# image formats include JPEG, BMP etc.# should be classic application scenarios, usually 20~100 images are picked out from test datasets# in addition, note that input images should cover typical scenarios# and try to avoid those overexposed, oversaturated, vague, # pure blank or pure white images# use ';' to seperate when there are multiple input nodescal_data_dir: './calibration_data_bgr_f32'# 如果输入的图片文件尺寸和模型训练的尺寸不一致时，并且preprocess_on为true，# 则将采用默认预处理方法(skimage resize)，# 将输入图片缩放或者裁减到指定尺寸，否则，需要用户提前把图片处理为训练时的尺寸# ----------------------------------------------------------------------------------# In case the size of input image file is different from that of in model training# and that preprocess_on is set to True,# shall the default preprocess method(skimage resize) be used# i.e., to resize or crop input image into specified size# otherwise user must keep image size as that of in training in advance# preprocess_on: False# 模型量化的算法类型，支持kl、max、default、load，通常采用default即可满足要求, 若为QAT导出的模型, 则应选择load# ------------------------------------------------------------------------------------# types of model quantization algorithms, usually default will meet the need# available options:kl, max, default and load# if converted model is quanti model exported from QAT , then choose `load`calibration_type: 'kl'# 编译器相关参数
# ----------------------------
# compiler related parameters
compiler_parameters:# 编译策略，支持bandwidth和latency两种优化模式;# bandwidth以优化ddr的访问带宽为目标；# latency以优化推理时间为目标# ------------------------------------------------------------------------------------------# compilation strategy, there are 2 available optimization modes: 'bandwidth' and 'lantency'# the 'bandwidth' mode aims to optimize ddr access bandwidth# while the 'lantency' mode aims to optimize inference durationcompile_mode: 'latency'# 设置debug为True将打开编译器的debug模式，能够输出性能仿真的相关信息，如帧率、DDR带宽占用等# -----------------------------------------------------------------------------------# the compiler's debug mode will be enabled by setting to True# this will dump performance simulation related information# such as: frame rate, DDR bandwidth usage etc.debug: False# 编译模型指定核数，不指定默认编译单核模型, 若编译双核模型，将下边注释打开即可# -------------------------------------------------------------------------------------# specifies number of cores to be used in model compilation # as default, single core is used as this value left blank# please delete the "# " below to enable dual-core mode when compiling dual-core model# core_num: 2# 优化等级可选范围为O0~O3# O0不做任何优化, 编译速度最快，优化程度最低,# O1-O3随着优化等级提高，预期编译后的模型的执行速度会更快，但是所需编译时间也会变长。# 推荐用O2做最快验证# ----------------------------------------------------------------------------# optimization level ranges between O0~O3# O0 indicates that no optimization will be made # the faster the compilation, the lower optimization level will be# O1-O3: as optimization levels increase gradually, model execution, after compilation, shall become faster# while compilation will be prolonged# it is recommended to use O2 for fastest verificationoptimize_level: 'O3'

执行03_build_X3.sh

如果上面三个脚本都执行成功的话我们将会在当前model_output目录下找到bin文件，这就是可以在X3派上运行的模型文件

2. 在旭日派X3上部署该模型

import cv2
import numpy as np
from hobot_dnn import pyeasy_dnn as dnndef convert_bgr_to_nv12(cv_image):yuv_image = cv2.cvtColor(cv_image, cv2.COLOR_BGR2YUV)y_channel = yuv_image[:, :, 0]u_channel = yuv_image[::2, ::2, 1]v_channel = yuv_image[::2, ::2, 2]uv_channel = np.empty((u_channel.shape[0], u_channel.shape[1] * 2), dtype=u_channel.dtype)uv_channel[:, ::2] = u_channeluv_channel[:, 1::2] = v_channelnv12_image = np.concatenate((y_channel.flatten(), uv_channel.flatten()))return nv12_imagedef process_frame(cv_image, models, original_width, original_height):# 将图像缩放到模型期望的尺寸cv_image_resized = cv2.resize(cv_image, (224, 224), interpolation=cv2.INTER_LINEAR)nv12_image = convert_bgr_to_nv12(cv_image_resized)# 使用模型进行推理outputs = models[0].forward(np.frombuffer(nv12_image, dtype=np.uint8))outputs = outputs[0].buffer# 假设模型输出是在224x224图像上的比例坐标x_ratio, y_ratio = outputs[0][0][0][0], outputs[0][1][0][0]# 将比例坐标转换为原始视频帧的像素坐标x_pixel = int(x_ratio * original_width)y_pixel = int(y_ratio * original_height)return x_pixel, y_pixeldef main():models = dnn.load('/root/model/resnet18_224x224_nv12.bin')cap = cv2.VideoCapture("/root/model/03.avi")# 确定视频编解码器和创建VideoWriter对象fourcc = cv2.VideoWriter_fourcc(*'XVID')out = cv2.VideoWriter('output.avi', fourcc, 20.0, (640, 480))while cap.isOpened():ret, frame = cap.read()if not ret:breakx, y = process_frame(frame, models,640,480)cv2.circle(frame, (x, y), radius=5, color=(0, 0, 255), thickness=-1)# 写入帧到输出文件out.write(frame)# cv2.imshow('Frame', frame)if cv2.waitKey(1) & 0xFF == ord('q'):breakcap.release()out.release()  # 释放VideoWriter对象cv2.destroyAllWindows()if __name__ == "__main__":main()