I'm trying to train an object detection model in Tensorflow 2. But since I went over to tensorflow 2 from 1 I seem to have problems. Whenever I start training. I get the same error shown in the following github thread https://github.com/tensorflow/models/issues/9706:
I have the same error if I use numpy 1.20.0 NotImplementedError: Cannot convert a symbolic Tensor (cond_2/strided_slice:0) to a numpy array.
if I use numpy 1.19.5 I get ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 88 from C header, got 80 from PyObject
Tried with TF 2.2.2 as well in both cases same errors
The only difference is that when I change python to 3.6 I get the same output as the last error message(I'm also using anaconda):
Traceback (most recent call last): File "model_main_tf2.py", line 31, in import tensorflow.compat.v2 as tf File "D:\Maurice_Doc\AI\anaconda3\envs\tensorflow\lib\site-packages\tensorflow_init_.py", line 41, in from tensorflow.python.tools import module_util as module_util File "D:\Maurice_Doc\AI\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python_init.py", line 39, in from tensorflow.python import pywrap_tensorflow as _pywrap_tensorflow File "D:\Maurice_Doc\AI\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\pywrap_tensorflow.py", line 83, in raise ImportError(msg) ImportError: Traceback (most recent call last): File "D:\Maurice_Doc\AI\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\pywrap_tensorflow.py", line 64, in from tensorflow.python._pywrap_tensorflow_internal import
- ImportError: DLL load failed: The specified module could not be found.
Failed to load the native TensorFlow runtime.
See https://www.tensorflow.org/install/errors
for some common reasons and solutions. Include the entire stack trace above this error message when asking for help.
I've followed the tutorial at: https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/training.html
from start to finish and it worked when I was following the TensorFlow 1x tutorial but for some reason, since they switched to Tensorflow 2x I get a lot of issues.
Does anybody know how to fix this issue?
