What is the reason for the InvalidArgumentError when adding an LSTM layer?

Question

Python

When adding an LSTM layer to a Keras model, an error occurs:
Traceback (most recent call last):
File "/opt/keras-query-classifier/venv_cpu/lib/python3.8/site-packages/tensorflow/python/framework/ops .py", line 1880, in _create_c_op
c_op = pywrap_tf_session.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Shape must be at least rank 3 but is rank 2 for '{{node BiasAdd}} = BiasAdd[T =DT_FLOAT, data_format="NCHW"](add, bias)' with input shapes: [?,80], [80].

until yesterday it was not, it is observed only on one machine.

here is the code:
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense, Activation, Dropout,
from tensorflow.keras.layers import Conv1D
from tensorflow.keras.layers import MaxPooling1D

model = Sequential()
model.add(Embedding(1000, 100, input_length=10))
model.add(Conv1D(filters=100, kernel_size=2, padding='same', activation='relu'))
model.add(Conv1D(filters=100, kernel_size=2, padding='same', activation='relu'))
model.add(MaxPooling1D(pool_size=2) )
model.add(LSTM(20))

Changing environment doesn't help.

Tell me vector, where to look for the problem?

Answer 1

In most cases, this error occurs when there are collisions between libraries.

Answer 2

Solution not found. As an option for yourself for the future - back up