我正在尝试使用Tensorflow Object Detection API对某些自定义数据集进行传输学习 .

启动训练命令时，训练永远不会开始，脚本似乎永远在运行 . 这是一些输出：

WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/contrib/slim/python/slim/learning.py:736: __init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
INFO:tensorflow:Restoring parameters from /Users/clementjoudet/Desktop/dev/teeth/models/transfer/ssd_mobilenet_v2_coco_2018_03_29/model.ckpt
INFO:tensorflow:Restoring parameters from /Users/clementjoudet/Desktop/dev/teeth/models/transfer/ssd_mobilenet_v2_coco_2018_03_29/model.ckpt
INFO:tensorflow:Starting Session.
INFO:tensorflow:Starting Session.
INFO:tensorflow:Saving checkpoint to path /Users/clementjoudet/Desktop/dev/teeth/models/transfer/train/model.ckpt
INFO:tensorflow:Saving checkpoint to path /Users/clementjoudet/Desktop/dev/teeth/models/transfer/train/model.ckpt
INFO:tensorflow:Starting Queues.
INFO:tensorflow:Starting Queues.
INFO:tensorflow:global_step/sec: 0
INFO:tensorflow:global_step/sec: 0
INFO:tensorflow:global_step/sec: 0
INFO:tensorflow:global_step/sec: 0
INFO:tensorflow:global_step/sec: 0
INFO:tensorflow:global_step/sec: 0
INFO:tensorflow:global_step/sec: 0
INFO:tensorflow:global_step/sec: 0

我尝试更改Tensorflow版本，从Models repo中提取，并使用不同的模型（Fastrcnn，SSD_mobilenet），但它始终是相同的 .

我正在使用https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md的模型

和https://github.com/tensorflow/models/tree/master/research/object_detection/samples/configs中的同名配置文件

我在配置文件中唯一改变的是：

  • 个类的数量（我的数据集有更少的类）

  • fine_tune_checkpoint路径

  • train和eval记录的输入路径标记映射路径

注意：当我在没有fine_tune_checkpoint的情况下开始训练时，训练正常 . 在尝试从tensorflow动物园导入模型时，它不起作用

这是我的文件夹树：

├── coco.config
├── eval
├── ssd_mobilenet_v2_coco_2018_03_29
│   ├── checkpoint
│   ├── frozen_inference_graph.pb
│   ├── model.ckpt.data-00000-of-00001
│   ├── model.ckpt.index
│   ├── model.ckpt.meta
│   ├── pipeline.config
│   └── saved_model
│       ├── saved_model.pb
│       └── variables
└── train
python tensorflow object-detection