I was trying to use the faster_rcnn_inception_v2_coco_2018_01_28 for my first object detection project. I was trying to train the model, and got this error. Before this error occurred, I was struggling with 'abs' being not found. I reinstalled tensorflow, and somehow it worked.
This is the code that I ran on cmd. If I need to post what's in train.py or any code that I should have posted here, let me know.
(tf1.12) C:\Users\EuisanKim\Desktop\tf1.12\model\research\object_detection>python legacy/train.py --logtostderr --train_dir=training/ --pipeline_config=training/faster_rcnn_inception_v2_pets.config
C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorflow\python\framework\dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorflow\python\framework\dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorflow\python\framework\dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorflow\python\framework\dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorflow\python\framework\dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorflow\python\framework\dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) WARNING: Logging before flag parsing goes to stderr. W0829 08:28:04.658330 10092 lazy_loader.py:50] The TensorFlow contrib module will not be included in TensorFlow 2.0. For more information, please see: * https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md * https://github.com/tensorflow/addons * https://github.com/tensorflow/io (for I/O related ops) If you depend on functionality not listed there, please file an issue.
W0829 08:28:04.851034 10092 deprecation_wrapper.py:119] From C:\Users\EuisanKim\Desktop\tf1.12\model\research\slim\nets\inception_resnet_v2.py:373: The name tf.GraphKeys is deprecated. Please use tf.compat.v1.GraphKeys instead.
W0829 08:28:04.878998 10092 deprecation_wrapper.py:119] From C:\Users\EuisanKim\Desktop\tf1.12\model\research\slim\nets\mobilenet\mobilenet.py:397: The name tf.nn.avg_pool is deprecated. Please use tf.nn.avg_pool2d instead.
W0829 08:28:04.907918 10092 deprecation_wrapper.py:119] From legacy/train.py:55: The name tf.logging.set_verbosity is deprecated. Please use tf.compat.v1.logging.set_verbosity instead.
W0829 08:28:04.908879 10092 deprecation_wrapper.py:119] From legacy/train.py:55: The name tf.logging.INFO is deprecated. Please use tf.compat.v1.logging.INFO instead.
W0829 08:28:04.913866 10092 deprecation_wrapper.py:119] From legacy/train.py:184: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.
W0829 08:28:04.916857 10092 deprecation.py:323] From C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\absl\app.py:251: main (from main) is deprecated and will be removed in a future version. Instructions for updating: Use object_detection/model_main.py. W0829 08:28:04.917856 10092 deprecation_wrapper.py:119] From legacy/train.py:90: The name tf.gfile.MakeDirs is deprecated. Please use tf.io.gfile.makedirs instead.
W0829 08:28:04.920847 10092 deprecation_wrapper.py:119] From legacy/train.py:107: The name tf.gfile.Copy is deprecated. Please use tf.io.gfile.copy instead.
Fatal Python error: Segmentation fault
Current thread 0x0000276c (most recent call first): File "C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 486 in copy_v2 File "C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 469 in copy File "legacy/train.py", line 108 in main File "C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorflow\python\util\deprecation.py", line 324 in new_func File "C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\absl\app.py", line 251 in _run_main File "C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\absl\app.py", line 300 in run File "C:\Users\EuisanKim\Anaconda3\envs\tf1.12\lib\site-packages\tensorflow\python\platform\app.py", line 40 in run File "legacy/train.py", line 184 in
What I did before running the code above are:
1) Annotating the data - I was using different sizes of pictures (Could this lead to this error?)
2) Creating the record files, label map file, and etc that are necessary for training
I just started to learn programming. I don't know much about what's happening with this problem. Please, help me. Thank you.
