First, comment out the code below if it's not what you meant.
-> #pillar_net.load_weights(os.path.join(MODEL_ROOT, "model.h5"))
in point_pillars_training_run.py
Second, you must modify the code below.
original: from tensorflow.python.keras.utils.data_utils import Sequence
-> from tensorflow.keras.utils import Sequence
in processors.py
( https://github.com/tensorflow/tensorflow/issues/36819 )
First, comment out the code below if it's not what you meant.
-> #pillar_net.load_weights(os.path.join(MODEL_ROOT, "model.h5")) in point_pillars_training_run.py
Second, you must modify the code below. original: from tensorflow.python.keras.utils.data_utils import Sequence -> from tensorflow.keras.utils import Sequence in processors.py ( https://github.com/tensorflow/tensorflow/issues/36819 )
And, if there is an error related to "cudnn", please refer to the link below. https://stackoverflow.com/questions/69879188/could-not-load-library-cudnn-cnn-infer64-8-dll-error-code-126