I have also faced the same error. This error occurs due to the incorrect path given into config file. if it is a Windows machine, make sure you use forward slash at the paths you write into the config file.
I am new to Tensorflow as well as Data Science. Recently, I wanted to train custom object detection.
Machine and Environment Types and Other Requirements:
At first I stored all my files in
C:\Users\Documents\TensorFlow\models\research
directory as it was giving error continuously while I try to run this from other folder.
then after copying all the files and folders of my custom object's to above directory, I started the venv of tensorflow_cpu in anaconda prompt and then I wrote following command:
python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/pipeline.config
Then the training began,
I have done all of this by following a blog. I wanted to keep my global loss at least 2. But suddenly without any intention to give keyboard interrupt I pressed ctrl+c and the train.py file terminated. Now when I re-run this, I get the following error:
(tensorflow_cpu) C:\Users\arfan\Documents\TensorFlow\models\research>python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/pipeline.config
WARNING:tensorflow:From C:\Anaconda3\envs\tensorflow_cpu\lib\site-packages\tensorflow\python\platform\app.py:125: main (from __main__) is deprecated and will be removed in a future version.
Instructions for updating:
Use object_detection/model_main.py.
W1118 23:02:23.971923 9792 tf_logging.py:125] From C:\Anaconda3\envs\tensorflow_cpu\lib\site-packages\tensorflow\python\platform\app.py:125: main (from __main__) is deprecated and will be removed in a future version.
Instructions for updating:
Use object_detection/model_main.py.
Traceback (most recent call last):
File "train.py", line 184, in <module>
tf.app.run()
File "C:\Anaconda3\envs\tensorflow_cpu\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
_sys.exit(main(argv))
File "C:\Anaconda3\envs\tensorflow_cpu\lib\site-packages\tensorflow\python\util\deprecation.py", line 306, in new_func
return func(*args, **kwargs)
File "train.py", line 180, in main
graph_hook_fn=graph_rewriter_fn)
File "C:\Users\arfan\Documents\TensorFlow\models\research\object_detection\legacy\trainer.py", line 248, in train
detection_model = create_model_fn()
File "C:\Users\arfan\Documents\TensorFlow\models\research\object_detection\builders\model_builder.py", line 122, in build
raise ValueError('Unknown meta architecture: {}'.format(meta_architecture))
ValueError: Unknown meta architecture: None
Can anyone please help? I am new to this field so please explain your answer. This is my first post here, extremely sorry if I make any unintentional mistake.
directory as it was giving error continuously while I try to run this from other folder.
then after copying all the files and folders of my custom object's to above directory, I started the venv of tensorflow_cpu in anaconda prompt and then I wrote following command:
directory as it was giving error continuously while I try to run this from other folder.
then after copying all the files and folders of my custom object's to above directory, I started the venv of tensorflow_cpu in anaconda prompt and then I wrote following command:
Then the training began,
I have also faced the same error. This error occurs due to the incorrect path given into config file. if it is a Windows machine, make sure you use forward slash at the paths you write into the config file.