I want to use Mask RCNN ot tf-models-official but it has to be with python 3.10 and tf 2.9.3. Tf versions for installing go up to 2.9.2 and then 2.10, if I try tf-models-official==2.9.3 it gives an error
(python_3_10) C:\Users\Carenne>pip install tf-models-official==2.9.3 WARNING: Ignoring invalid distribution -rotobuf (c:\users\carenne\anaconda3\envs\python_3_10\lib\site-packages) ERROR: Could not find a version that satisfies the requirement tf-models-official==2.9.3 (from versions: 0.0.2.dev0, 0.0.3.dev0, 0.0.3.dev1, 2.1.0.dev1, 2.1.0.dev2, 2.2.0, 2.2.1, 2.2.2, 2.3.0, 2.4.0, 2.5.0, 2.5.1, 2.6.0, 2.6.1, 2.7.0, 2.7.1, 2.7.2, 2.8.0, 2.9.0, 2.9.1, 2.9.2, 2.10.0, 2.10.1, 2.11.0, 2.11.2, 2.11.3, 2.11.4, 2.11.5, 2.11.6, 2.12.0) ERROR: No matching distribution found for tf-models-official==2.9.3
What would be better for installation: tf 2.10 or 2.9.2? I can't change the tf version because I am working over a JN on Watson IBM and this is the only available environment
Also, I have trained the MaskRCNN model using https://github.com/BupyeongHealer/Mask_RCNN_tf_2.x/tree/master but now I can't use this with tf 2.9.3. Any tips on how to migrate from thsi deployment to tf-models-official? I can't find any examples on how to do this, any help would be greatly appreciated.
