我在 githug 上克隆了 tensorflow 对象检测模型: github link
我想用我自己的数据(331 只萨摩耶狗的图像)训练这个模型，遵循这个博客教程 click here
我的步骤:
- 创建了 PASCAL VOC 格式的数据集；
- 下载再训练模型( ssd_mobilenet_v1_coco_11_06_2017.tar.gz )
- 更改配置文件(ssd_mobilenet_v1_pets.config)
- 通过以下代码启动训练过程:
python object_detection/train.py \ --logtostderr \ --pipeline_config_path=./samoyed_test_and_train/training/ssd_mobilenet_v1_pets.config \ --train_dir=./samoyed_test_and_train/data/train.record
但我收到错误，我的操作系统是 MacOS，我在 AWS 上试过，同样的问题出现了，你能找出我的错误吗？错误:
INFO:tensorflow:Summary name Learning Rate is illegal; using Learning_Rate instead.
WARNING:tensorflow:From /Users/zhaoenpei/Desktop/dabai-robot-arm/experiments/models/object_detection/meta_architectures/ssd_meta_arch.py:579: all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Please use tf.global_variables instead.
INFO:tensorflow:Summary name /clone_loss is illegal; using clone_loss instead.
2017-08-01 10:34:42.992224: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-01 10:34:42.992254: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-08-01 10:35:00.359032: I tensorflow/core/common_runtime/simple_placer.cc:675] Ignoring device specification /device:GPU:0 for node 'prefetch_queue_Dequeue' because the input edge from 'prefetch_queue' is a reference connection and already has a device field set to /device:CPU:0
INFO:tensorflow:Restoring parameters from /Users/zhaoenpei/Desktop/dabai-robot-arm/experiments/models/samoyed_test_and_train/training/model.ckpt
INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.FailedPreconditionError'>, ./samoyed_test_and_train/data/train.record/graph.pbtxt.tmpf4587d1958df43cbaa9a0d7a04199f6f
2017-08-01 10:35:29.556458: E tensorflow/core/util/events_writer.cc:62] Could not open events file: ./samoyed_test_and_train/data/train.record/events.out.tfevents.1501554929.MacBook-Pro.local: Failed precondition: ./samoyed_test_and_train/data/train.record/events.out.tfevents.1501554929.MacBook-Pro.local
2017-08-01 10:35:29.556480: E tensorflow/core/util/events_writer.cc:95] Write failed because file could not be opened.
Traceback (most recent call last):
File "object_detection/train.py", line 198, in <module>
tf.app.run()
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "object_detection/train.py", line 194, in main
worker_job_name, is_chief, FLAGS.train_dir)
File "/Users/zhaoenpei/Desktop/dabai-robot-arm/experiments/models/object_detection/trainer.py", line 290, in train
saver=saver)
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/contrib/slim/python/slim/learning.py", line 732, in train
master, start_standard_services=False, config=session_config) as sess:
File "/usr/local/Cellar/python/2.7.13/Frameworks/Python.framework/Versions/2.7/lib/python2.7/contextlib.py", line 17, in __enter__
return self.gen.next()
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 964, in managed_session
self.stop(close_summary_writer=close_summary_writer)
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 792, in stop
stop_grace_period_secs=self._stop_grace_secs)
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/training/coordinator.py", line 389, in join
six.reraise(*self._exc_info_to_raise)
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 953, in managed_session
start_standard_services=start_standard_services)
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 709, in prepare_or_wait_for_session
self._write_graph()
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 612, in _write_graph
self._logdir, "graph.pbtxt")
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/framework/graph_io.py", line 67, in write_graph
file_io.atomic_write_string_to_file(path, str(graph_def))
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/lib/io/file_io.py", line 418, in atomic_write_string_to_file
write_string_to_file(temp_pathname, contents)
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/lib/io/file_io.py", line 305, in write_string_to_file
f.write(file_content)
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/lib/io/file_io.py", line 101, in write
self._prewrite_check()
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/lib/io/file_io.py", line 87, in _prewrite_check
compat.as_bytes(self.__name), compat.as_bytes(self.__mode), status)
File "/usr/local/Cellar/python/2.7.13/Frameworks/Python.framework/Versions/2.7/lib/python2.7/contextlib.py", line 24, in __exit__
self.gen.next()
File "/Users/zhaoenpei/.virtualenvs/python_virtual_1/lib/python2.7/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.FailedPreconditionError: ./samoyed_test_and_train/data/train.record/graph.pbtxt.tmpf4587d1958df43cbaa9a0d7a04199f6f
请您参考如下方法:
train_dir 标志用于指向某个(通常为空)目录，您的训练日志和检查点将在训练期间写入该目录。例如，它可能类似于 train_dir=/tmp/training_directory。看起来您正在尝试将其指向您的数据集 --- 配置文件应该已经指向该数据集。
