Maybe try:
%tensorflow_version 1.x
from https://colab.research.google.com/notebooks/tensorflow_version.ipynb ?

1.! python -m pip install Keras==2.3.1 tensorflow==2.1.0
2. import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
print(tf.version)

After executing the requirements file we need to run the above two steps to run the code in colab

After following your instructions from the above comment on colab, it gives this error after first epoch:
Epoch 1/70
74/74 [==============================] - 273s 4s/step - loss: 0.4780 - dice_coef: 0.5583 - val_loss: 5.9511 - val_dice_coef: 0.2558
NotImplementedError Traceback (most recent call last)
in ()
----> 1 history = model.fit(train_generator, validation_data=valid_generator, callbacks=callbackslist, epochs=70, verbose=1)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/resource_variable_ops.py in numpy(self)
582 return self.read_value().numpy()
583 raise NotImplementedError(
--> 584 "numpy() is only available when eager execution is enabled.")
585
586 @deprecated(None, "Prefer Dataset.range instead.")

NotImplementedError: numpy() is only available when eager execution is enabled.

I tried:
import tensorflow.compat.v1 as tf
tf.enable_eager_execution()

tf.disable_v2_behavior()
print(tf.version)

Still same error....@Swathi-Gupta