【吴恩达深度学习编程作业问题汇总】4.3目标检测——车辆识别

迷南。 2022-12-23 00:47 216阅读 0赞

## 问题描述 ##

最近在学习吴恩达深度学习系列课程，做到编程作业4.3车辆识别时因为TensorFlow和Keras版本不兼容而出现各种问题，查找了一些资料后好多人都提出降低TF版本，不放弃我最后的倔强，最终还是把所有问题逐一解决了：）

**查看Python、TensorFlow、Keras版本**：我的Python版本3.7.0，TensorFlow版本2.3.1，Keras版本2.4.3。

import sys
    import tensorflow as tf
    import keras
    print(sys.version)          # 3.7.0 (v3.7.0:1bf9cc5093, Jun 27 2018, 04:59:51) [MSC v.1914 64 bit (AMD64)]
    print(tf.__version__)       # 之前是1.15.3，现在用的版本升级到了2.3.1
    print(keras.__version__)    # 2.4.3

[Keras与TensorFlow关系][Keras_TensorFlow]

## 1.AttributeError: 'tensorflow’模块没有’space\_to\_depth’属性 ##

#### 报错描述： ####

Traceback (most recent call last):
      File "G:/Project/PYTHON/Demo01/Deep_Learning/test4_3/车辆识别.py", line 225, in <module>
        yolo_model = load_model("model_data/yolov2.h5")
    	......
      File "C:\Users\Oscar\Desktop\yad2k\yad2k\models\keras_yolo.py", line 32, in space_to_depth_x2
    AttributeError: module 'tensorflow' has no attribute 'space_to_depth'

#### 解决方法： ####

我使用的是TensorFlow2.1以上版本，源编译前的H5文件中使用了tf.space\_to\_depth，TF2.1之后的版本改成了tf.nn.space\_to\_depth，需要自己重新生成H5文件。我参考以下三篇文章自己生成了yolo.h5文件，注意要将yad2k/models/keras\_yolo.py第31行改为tf.nn.space\_to\_depth。

[tf2.1下生成yolo.h5文件][tf2.1_yolo.h5]  
[yolo.h5文件问题的解决 - 吴恩达深度学习：目标检测之YOLO算法][yolo.h5_ - _YOLO]  
[关于吴恩达车辆识别代码出错的问题][Link 1])

## 2.TypeError：获取参数None具有无效的类型<class’NoneType’> ##

#### 报错描述： ####

Traceback (most recent call last):
      File "G:/Project/PYTHON/Demo01/Deep_Learning/test4_3/车辆识别.py", line 246, in <module>
        scores, boxes, classes = yolo_eval(yolo_outputs, image_shape)
      File "G:/Project/PYTHON/Demo01/Deep_Learning/test4_3/车辆识别.py", line 188, in yolo_eval
        scores, boxes, classes = yolo_non_max_suppression(scores, boxes, classes, max_boxes, iou_threshold)
      File "G:/Project/PYTHON/Demo01/Deep_Learning/test4_3/车辆识别.py", line 123, in yolo_non_max_suppression
        tf.compat.v1.keras.backend.get_session().run(tf.compat.v1.variables_initializer([max_boxes_tensor]))     # 初始化变量max_boxes_tensor
      File "F:\Python\lib\site-packages\tensorflow\python\client\session.py", line 958, in run
    <tf.Variable 'Variable:0' shape=() dtype=int32, numpy=10>
        run_metadata_ptr)
      File "F:\Python\lib\site-packages\tensorflow\python\client\session.py", line 1166, in _run
        self._graph, fetches, feed_dict_tensor, feed_handles=feed_handles)
      File "F:\Python\lib\site-packages\tensorflow\python\client\session.py", line 477, in __init__
        self._fetch_mapper = _FetchMapper.for_fetch(fetches)
      File "F:\Python\lib\site-packages\tensorflow\python\client\session.py", line 263, in for_fetch
        (fetch, type(fetch)))
    TypeError: Fetch argument None has invalid type <class 'NoneType'>

#### 解决方法： ####

这个错误最恶心，我找了很久才解决。看到这个错误时找了一个很全的参考文章： [Tensorflow报错：TypeError: Fetch argument None has invalid type class ‘NoneType’][Tensorflow_TypeError_ Fetch argument None has invalid type class _NoneType] ，并参考了github说是大部分错误的原因都是某一个op重新赋值导致变量变成None，但是还是没有解决。仔细查看代码发现问题出在非最大值抑制函数中创建会话并运行初始化变量max\_boxes\_tensor这一步，后来发现TensorFlow 2.x是默认开启 **eager execution** 的，eager execution提供了一种命令式的编程环境，不需要构建图直接可以运行（参考文章：[tensorflow 2.0系列（3）：eager execution和计算图][tensorflow 2.0_3_eager execution]）。而在老版本中需要先构建计算图再执行。我这里还是用的老版本的代码，所有需要禁用：

import tensorflow as tf
    tf.compat.v1.disable_eager_execution()

## 3.OSError：不能打开路径 ##

#### 报错描述： ####

Traceback (most recent call last):
      File "G:/Project/PYTHON/Demo01/Deep_Learning/test4_3/车辆识别.py", line 288, in <module>
        out_scores, out_boxes, out_classes = predict(sess, "test.jpg")
      File "G:/Project/PYTHON/Demo01/Deep_Learning/test4_3/车辆识别.py", line 272, in predict
        draw_boxes(image, out_scores, out_boxes, out_classes, class_names, colors)
      File "G:\Project\PYTHON\Demo01\Deep_Learning\test4_3\yolo_utils.py", line 52, in draw_boxes
        font = ImageFont.truetype(font='font/FiraMono-Medium.otf',size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
      File "F:\Python\lib\site-packages\PIL\ImageFont.py", line 648, in truetype
        return freetype(font)
      File "F:\Python\lib\site-packages\PIL\ImageFont.py", line 645, in freetype
        return FreeTypeFont(font, size, index, encoding, layout_engine)
      File "F:\Python\lib\site-packages\PIL\ImageFont.py", line 194, in __init__
        font, size, index, encoding, layout_engine=layout_engine
    OSError: cannot open resource

#### 解决方法： ####

这是路径问题：图中绘制边界框那行代码有个draw\_boxes()，需要把这个函数中第一行的font文件路径改成你自己的(默认是在当前路径下找)。还有保存绘制图片image.save()那一行默认保存在当前路径下的out文件夹下，如果没有这个文件夹就报错。

## 之前在运行时还有个报错： ##

> raise TypeError Tensor is unhashable. TypeError: Tensor is unhashable. Instead, use tensor.ref as the key.

不知道该怎么复现了，当时用的是这个解决办法：[FailedPreconditionError: Error while reading resource variable was uninitialized][FailedPreconditionError_ Error while reading resource variable was uninitialized]

[Keras_TensorFlow]: https://blog.csdn.net/XYKenny/article/details/90712476?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522160592641119725255523934%2522%252C%2522scm%2522%253A%252220140713.130102334..%2522%257D&request_id=160592641119725255523934&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~all~top_click~default-1-90712476.pc_search_result_no_baidu_js&utm_term=keras%E5%92%8Ctensorflow%E7%9A%84%E5%85%B3%E7%B3%BB&spm=1018.2118.3001.4449
[tf2.1_yolo.h5]: https://blog.csdn.net/weixin_44750583/article/details/105716221
[yolo.h5_ - _YOLO]: https://blog.csdn.net/Solo95/article/details/85262828
[Link 1]: https://www.cnblogs.com/pengzhi12345/p/11900994.html
[Tensorflow_TypeError_ Fetch argument None has invalid type class _NoneType]: https://blog.csdn.net/edward_zcl/article/details/89338166
[tensorflow 2.0_3_eager execution]: https://blog.csdn.net/happyhorizion/article/details/103849408?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522160600739119725266908880%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fall.%2522%257D&request_id=160600739119725266908880&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~all~first_rank_v2~rank_v28-5-103849408.pc_search_result_no_baidu_js&utm_term=tf.compat.v1.disable_eager_exe&spm=1018.2118.3001.4449
[FailedPreconditionError_ Error while reading resource variable was uninitialized]: http://www.ai111.vip/thread-995-1-1.html