Michael Hammond

Hello, PhasedLSTM-Keras user here. I'm using containerization and a custom PC for the project as needed for what I'm doing. I don't know the scope of what you're doing, but...

> > > @AutoUpdatingBSoD I'm not familiar with Anaconda containers, how can they make this code work with implementations in tensorflow 2 ? @nk-fouque Answer: you don't. containerized environments are,...

> > > Hello, PhasedLSTM-Keras user here. I'm using containerization and a custom PC for the project as needed for what I'm doing. > > I don't know the scope...

This is a long shot, but have you tried Tensorflow's Functional Model? Everywhere I'm reading is saying as a general rule, that one's better at basically everything. I'm no ML...

How did they run the Sequential model, because it's obvious that the Sequential Model works to some extent with Keras/TF 2+ (if it didn't the example code wouldn't run).

What I think is the real issue, for clarity, is that we're both not defining the model properly.

Sorry, I wasn't clear. What I meant was what does the statement look like where you're actually adding the model? I.E. The part where the program actually crashes.

The reason I ask is because I get the same thing even with a similar setup, that's why I suspect it's something else.

What I'm saying is this: ``` TF Version: 1.15.0 Keras Version: 2.1.5 tf.keras Version: 2.2.4-tf WARNING:tensorflow:From C:\Users\unrea\anaconda3\envs\tf15\lib\site-packages\keras\backend\tensorflow_backend.py:68: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead. Traceback (most recent call...

That said, I'm no ML expert. I'm just a silly person on the internet who happens to know how to write a little code.