Hi,
I am writing this thread to request help in creating deep learning strategies with zorro and Keras / Tensorflow.
I have done the following:
- Download and install R 64 bit for Windows
- Edit Zorro.ini and enter the path to the R terminal on my PC, f.i. "C:\Program Files\R\R-4.2.1\bin\x64\Rterm.exe".
- Started the R x64 console. Enter the command install.packages("keras") and hit <Return>.
- Let Keras automatically install Miniconda and Tensorflow. The commands: library('keras') - install_keras().

I am getting the following results as printed on the rstudio log comments:

ERROR: Could not find a version that satisfies the requirement tensorflow==2.15.* (from versions: 2.16.0rc0, 2.16.1, 2.16.2, 2.17.0rc0, 2.17.0rc1, 2.17.0)
ERROR: No matching distribution found for tensorflow==2.15.*
Error: Error installing package(s): "\"tensorflow==2.15.*\"", "tensorflow-hub", "tensorflow-datasets", "scipy", "requests", "Pillow", "h5py", "pandas", "pydot"

The results are gotten from following the instructions in the manual. Are the installations successful?

Furthermore, in the example use Keras in your strategy, where do i paste the sample code? in the zorro editor ? in the R editor? I need more information on how to backtest in zorro using Keras / Tensorflow please.

Thanks and looking forward to your replies.

using a different method, i was able to install TensorFlow. It says Keras is now integrated into TensorFlow, so by installing TensorFlow, you also get Keras.