深度学习-卷积神经网络-目标检测之YOLOV3模型-代码运行图片检测实践2

系列文章

深度学习-卷积神经网络（目标检测环境搭建）-TensorFlow及Keras环境搭建&详细安装教程

深度学习-卷积神经网络-目标检测之YOLOV3模型-代码运行图片检测实践1

相关文章

深度学习-卷积神经网络-实例及代码0.8—基于最小均方误差的线性判别函数参数拟合训练

深度学习-卷积神经网络-实例及代码0.9—MNIST数据集介绍、下载及基本操作

深度学习-卷积神经网络-实例及代码1（入门）—利用Tensorflow和mnist数据集训练单层前馈神经网络/感知机实现手写数字识别

深度学习-卷积神经网络-实例及代码2（初级）—利用Tensorflow和mnist数据集训练简单的深度网络模型实现手写数字识别

深度学习-卷积神经网络-实例及代码3（图像分类LeNet5模型）—利用Tensorflow和mnist数据集训练LeNet5-CNN模型实现手写数字识别

 

前一篇文章主要通过修改yolo_video.py文件实现YOLOV3-Keras版本的执行图片检测

这里介绍另一种执行图片检测的实践途径，实验证明也是可行的；并且为后面使用自己的数据集进行训练做准备

使用的代码版本仍然是github上的qqwweee/keras-yolo3 Keras实现版本

在Windows环境下使用CPU进行检测

（操作系统：Windows 10专业版 64位）

（CPU：Intel(R) Core(TM) i5-4590 CPU@3.30GHz，内存8G）

执行下面YOLOV3的检测程序前，需要完成前序文章中的TensorFlow和Keras环境搭建和安装等内容

（如果要执行视频检测还要安装opencv的python版本等）

1，下载YOLOV3-Keras项目

从这里下载原始项目文件：Github上qqwweee-keras版本的YOLOV3实现

文后附上了该项目的具体说明内容

使用Pycharm软件打开下载解压后的keras-yolov3项目

（我这里换了个项目名字：KerasYolo3Test2）

2，修改代码——yolo_video.py（红色字体表示和前一篇文章处理方式有不同的地方，下同）

注释掉原有代码，修改为以下

#添加的代码
def detect_img(yolo,img_path='test.png'):
    image=Image.open(img_path)
    import time
    t1=time.time()
    r_image=yolo.detect_image(image)
    print('time:{}'.format(time.time()-t1))
    r_image.show()
    yolo.close_session()
if __name__=='__main__':
    detect_img(YOLO(),img_path='image/car3.jpg')

 

3,修改代码——yolo.py

#添加的代码
import os
from keras.utils import multi_gpu_model

os.environ["CUDA_VISIBLE_DEVICES"] = "-1"

设置-1表明使用CPU训练，否则会报错：finished with exit code -1073740791 (0xC0000409)

 

4，下载YOLOV3官网上在COCO数据集上训练完成的权重文件yolov3.weights

进入YOLOV3官网链接：https://pjreddie.com/darknet/yolo/

找到 Performance on the COCO Dataset，其中有一行如下：
YOLOv3-416    COCO trainval    test-dev    55.3    65.86 Bn    35    cfg    weights

点击weights链接完成权重文件yolov3.weights的下载
 

5，执行代码convert.py,根据下载的权重文件生成模型
在pycharm中右键项目或项目文件，选择Open in Terminal
输入python convert.py yolov3.cfg yolov3.weights model_data/yolo.h5

完成模型的生成，在项目的model_data文件夹下可以看到yolo.h5

 

6，执行图片检测
直接run运行yolo_video.py 文件

检测过程及结果：

runfile('E:/PythonProject2020-PCnew/MyPythonTest/KerasYolo3Test2/yolo_video.py', wdir='E:/PythonProject2020-PCnew/MyPythonTest/KerasYolo3Test2')
Using TensorFlow backend.
2020-10-15 20:28:48.558479: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_100.dll'; dlerror: cudart64_100.dll not found
2020-10-15 20:28:48.558770: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2020-10-15 20:29:01.265687: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'nvcuda.dll'; dlerror: nvcuda.dll not found
2020-10-15 20:29:01.265957: E tensorflow/stream_executor/cuda/cuda_driver.cc:318] failed call to cuInit: UNKNOWN ERROR (303)
2020-10-15 20:29:01.344558: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: USER-PC
2020-10-15 20:29:01.344968: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: USER-PC
2020-10-15 20:29:01.345497: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
WARNING:tensorflow:From C:\Users\USER\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
model_data/yolo.h5 model, anchors, and classes loaded.
WARNING:tensorflow:From C:\Users\USER\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow_core\python\ops\array_ops.py:1475: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
(416, 416, 3)
2020-10-15 20:29:16.030648: E tensorflow/core/grappler/optimizers/meta_optimizer.cc:533] remapper failed: Invalid argument: Subshape must have computed start >= end since stride is negative, but is 0 and 2 (computed from start 0 and end 9223372036854775807 over shape with rank 2 and stride-1)
2020-10-15 20:29:16.613699: E tensorflow/core/grappler/optimizers/meta_optimizer.cc:533] remapper failed: Invalid argument: Subshape must have computed start >= end since stride is negative, but is 0 and 2 (computed from start 0 and end 9223372036854775807 over shape with rank 2 and stride-1)
Found 4 boxes for img
truck 0.31 (261, 415) (328, 495)
truck 0.96 (267, 353) (363, 489)
car 0.70 (603, 229) (633, 267)
car 0.88 (437, 376) (470, 414)
3.7307661
time:3.730863571166992