简体   繁体   English

使用Tensorflow的对象检测API用我自己的数据集训练对象检测器时出错

[英]Error while training an object detector with my own dataset using Tensorflow's Object Detection API

I'm working on training an object detector with tensor flow's object detector API. 我正在使用张量流的对象检测器API训练对象检测器。 I'm following this link to train an object detector with my own dataset. 我正在跟踪此链接,以使用自己的数据集训练对象检测器。 Everything seems to be fine until i started the training process (locally): 直到我开始(本地)培训过程,一切似乎都还不错:

python /Users/vinayakpahalwan/models/research/object_detection/train.py --logtostderr --train_dir=/Users/vinayakpahalwan/Desktop/ObjectDetection/training/ --pipeline_config_path=/Users/vinayakpahalwan/Desktop/ObjectDetection/training/ssd_mobilenet_v1_coco.config

I'm getting the following error : 我收到以下错误

Traceback (most recent call last):
  File "builders/model_builder_test.py", line 21, in <module>
    from object_detection.builders import model_builder
  File "/Users/vinayakpahalwan/models/research/object_detection/builders/model_builder.py", line 23, in <module>
    from object_detection.builders import matcher_builder
  File "/Users/vinayakpahalwan/models/research/object_detection/builders/matcher_builder.py", line 19, in <module>
    from object_detection.matchers import bipartite_matcher
  File "/Users/vinayakpahalwan/models/research/object_detection/matchers/bipartite_matcher.py", line 20, in <module>
    from tensorflow.contrib.image.python.ops import image_ops
ImportError: No module named 'tensorflow.contrib.image'

I'm kinda stuck here as of now, any workaround for that? 到目前为止,我还停留在这里,对此有任何解决方法?

I guess i have installed the object detection API correctly as per this link : 我想我已经按照以下链接正确安装了对象检测API:

Vinayaks-MacBook-Air:object_detection vinayakpahalwan$ python builders/model_builder_test.py
...........
----------------------------------------------------------------------
Ran 11 tests in 0.070s

OK

The error message is saying that it cannot locate the file tensorflow/contrib/image . 错误消息表明它无法找到文件tensorflow / contrib / image

Since you are using Tensorflow version 0.12.1, looking inside tensorflow/contrib , the folder image does not exist yet. 由于您使用的是Tensorflow版本0.12.1,因此在tensorflow / contrib内部查找时 ,文件夹图像尚不存在。 This is introduced from version 1.0 as seen here . 这是从1.0版本引入看到这里

Your workaround at this point is updating TS. 此时的解决方法是更新TS。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

相关问题 使用 TensorFlow 进行目标检测器训练 - Object Detector Training using TensorFlow TensorFlow对象检测API训练错误 - TensorFlow Object Detection API training error 在Tensorflow中为对象检测教程创建我自己的数据集的问题 - Issue creating my own dataset for the object detection tutorial from Tensorflow 在tensorflow对象检测API中进行训练时改组如何工作 - How does shuffling work while training in tensorflow object detection API 如何使用来自 Tensorflow 对象检测 API 的 Mask-RCNN 模型创建自己的数据集? - How to create own dataset for using Mask-RCNN models from the Tensorflow Object Detection API? 训练张量流对象检测关于检查点错误的错误 - Error while training tensorflow object detection about checkpoint error 缺少用于在 TensorFlow 的对象检测 API 中进行训练的模块和属性 - Missing modules and attributes for training in TensorFlow's Object Detection API 如何减少 Tensorflow 的对象检测 API 中的训练步骤数? - How to reduce the number of training steps in Tensorflow's Object Detection API? 使用张量流训练对象检测模型时,错误索引 [0] = 0 不在 [0, 0) 中 - Error indices[0] = 0 is not in [0, 0) while training an object-detection model with tensorflow 在使用Tensorflow对象检测API进行训练时,我如何知道步骤总数? - How do I know the total number of steps while training using Tensorflow Object Detection API?
 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM