Tensorflow and keras versions not compatible

[AnwarsaeedDMU]

I installed tensorflow and keras according to the requirement but it still gives me an error on every different step, mostly from tensorflow-backend.. I tried to upgrade tensorflow and keras versions sometimes but it giving me a new error. `Package Version

---

absl-py 1.4.0 astor 0.8.1 certifi 2022.12.7 colorama 0.4.6 gast 0.5.3 google-pasta 0.2.0 grpcio 1.51.3 h5py 3.8.0 importlib-metadata 6.0.0 Keras 2.2.4 Keras-Applications 1.0.8 keras-bert 0.80.0 keras-embed-sim 0.10.0 keras-layer-normalization 0.16.0 keras-multi-head 0.29.0 keras-pos-embd 0.13.0 keras-position-wise-feed-forward 0.8.0 Keras-Preprocessing 1.1.2 keras-self-attention 0.51.0 keras-transformer 0.40.0 Markdown 3.4.1 MarkupSafe 2.1.2 mock 5.0.1 numpy 1.21.6 pip 22.3.1 protobuf 3.20.1 PyYAML 6.0 scipy 1.7.3 setuptools 65.6.3 six 1.16.0 tensorboard 1.13.1 tensorflow-estimator 1.13.0 tensorflow-gpu 1.13.1 termcolor 2.2.0 tqdm 4.65.0 typing_extensions 4.5.0 Werkzeug 2.2.3 wheel 0.38.4 wincertstore 0.2 wrapt 1.15.0 zipp 3.15.0`

after that, it kind of run a little bit giving me result until train_data len: 56195 dev_data len: 4999 test_data len: 5000 but after every run, it gave me new attribute error, I tried to solve a lot but still more such as `File File "C:\Users\Usuario\anaconda3\envs\casnew\lib\site-packages\keras\engine\base_layer.py", line 1311, in _collect_previous_mask mask = node.output_masks[tensor_index] AttributeError: 'Node' object has no attribute 'output_masks'

I don't know how to solve this issue and what will be the perfect versions that will work well together. I am using python 3.7 and have CUDA on my system (have Gpu GTX 1650), OS Windows 10, and PYCharm for python code. if anybody run this code please suggest me some best solution for it.