Boris Treukhov

If this is MIT lab, I had the same problem because was referencing ` b` from the context instead of ` self.b` , but please keep this post for future...

It's sad it was never implemented, rest in peace. I spent a lot of time only to discover that this option simply didn't exist.

> I am using the same machine, also referring `self.b` and getting the same error. Is there any way to rectify this issue? See another issue https://github.com/aamini/introtodeeplearning/issues/116 If you re...

It sems that to get deterministic behavior in the latest Tensor Flow you need to use ``` tf.keras.utils.set_random_seed(1) tf.config.experimental.enable_op_determinism() ``` However this will not solve the problem, as you need...

Yes, the suggested PR by prashantkhurana works for me. Maybe the version of mitdeeplearning should be upped. I use NVidia CUDA RTX A5000 with x64 ubuntu, tensorflow 2.12, python 3.11...

> Still getting this error on colab even after replacing tf.random.set_seed(1) with tf.keras.utils.set_random_seed(1) tf.config.experimental.enable_op_determinism() I think is's because mitdeeplearning library file mitdeeplearning/lab1.py need to be patched also with the new...