Code Snippet:
import functools import tensorflow as tf from object_detection.core import box_predictor from object_detection.utils import static_shape
slim = tf.contrib.slim
Error Message:
Traceback (most recent call last): File "E:\uav\TFODCourse\Tensorflow\models\research\object_detection\builders\model_builder_tf2_test.py", line 24, in from object_detection.builders import model_builder File "E:\uav\TFODCourse\tfod\lib\site-packages\object_detection\builders\model_builder.py", line 22, in from object_detection.builders import box_predictor_builder File "E:\uav\TFODCourse\tfod\lib\site-packages\object_detection\builders\box_predictor_builder.py", line 22, in from object_detection.predictors import mask_rcnn_box_predictor File "E:\uav\TFODCourse\tfod\lib\site-packages\object_detection\predictors\mask_rcnn_box_predictor.py", line 21, in
slim = tf.contrib.slim AttributeError: module 'tensorflow' has no attribute 'contrib'
I am running a Custom Object Detection Model on Jupyter Notebook for tensorflow version of 2.15.0<=.
Can anyone help me to debug the error without switching to TF1.X? Thank You
I have tried the solution provided earlier on the forum regarding the same i.e. to downgrade from TF2.0 to TF1.0 and like wise every solution but getting the same error.