search

EdjeElectronics / TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10

How to train a TensorFlow Object Detection Classifier for multiple object detection on Windows
Apache License 2.0
2.93k stars 1.3k forks source link

Error when executing: python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config #492

Open jk0324 opened 4 years ago

jk0324 commented 4 years ago

Hello, i am now in the training part, but it shows the error below. Can you guys help me fix it? C:\tensorflow1\models\research\object_detection>python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config

WARNING:tensorflow:From C:\Users\Hp\Anaconda3\envs\tensorflow1\lib\site-packages\tensorflow_core\python\ops\distributions\distribution.py:265: ReparameterizationType.init (from tensorflow.python.ops.distributions.distribution) is deprecated and will be removed after 2019-01-01. Instructions for updating: The TensorFlow Distributions library has moved to TensorFlow Probability (https://github.com/tensorflow/probability). You should update all references to use tfp.distributions instead of tf.distributions. WARNING:tensorflow:From C:\Users\Hp\Anaconda3\envs\tensorflow1\lib\site-packages\tensorflow_core\python\ops\distributions\normal.py:274: RegisterKL.init (from tensorflow.python.ops.distributions.kullback_leibler) is deprecated and will be removed after 2019-01-01. Instructions for updating: The TensorFlow Distributions library has moved to TensorFlow Probability (https://github.com/tensorflow/probability). You should update all references to use tfp.distributions instead of tf.distributions. Traceback (most recent call last): File "train.py", line 47, in import tensorflow as tf File "C:\Users\Hp\Anaconda3\envs\tensorflow1\lib\site-packages\tensorflow__init.py", line 99, in from tensorflow_core import * File "C:\Users\Hp\Anaconda3\envs\tensorflow1\lib\site-packages\tensorflow_core__init__.py", line 32, in from tensorflow._api.v1 import app File "C:\Users\Hp\Anaconda3\envs\tensorflow1\lib\site-packages\tensorflow_core_api\v1\app\init__.py", line 10, in from tensorflow.python.platform.app import run File "C:\Users\Hp\Anaconda3\envs\tensorflow1\lib\site-packages\tensorflow_core\python\platform\app.py", line 23, in from absl.app import run as _run File "C:\Users\Hp\Anaconda3\envs\tensorflow1\lib\site-packages\absl\app.py", line 26, in from object_detection import model_lib File "C:\tensorflow1\models\research\object_detection\model_lib.py", line 27, in from object_detection import eval_util File "C:\tensorflow1\models\research\object_detection\eval_util.py", line 31, in from object_detection.core import box_list_ops File "C:\tensorflow1\models\research\object_detection\core\box_list_ops.py", line 34, in from object_detection.utils import ops File "C:\tensorflow1\models\research\object_detection\utils\ops.py", line 317, in dtype=tf.float32): AttributeError: module 'tensorflow' has no attribute 'float32'

QuickLearner171998 commented 4 years ago

https://stackoverflow.com/questions/51654346/attributeerror-module-tensorflow-has-no-attribute-float32