Tutorial 1 training still get nan loss about deep-learning-for-causal-inference HOT 4 CLOSED

And also Tutorial 3: Semi-parametric extensions to TARNet get nan loss.

Why get nan loss? Is the tensorflow version or GPU problem?

from deep-learning-for-causal-inference.

Thanks for letting me know. I'll look into it as soon as I get the chance!

Best,
Bernie

from deep-learning-for-causal-inference.

Hi Xiaogang,

I just tried the short tutorial 1 again and get no issues, using either CPU or the T4 GPU on collab. In general, using GPUs is probably slower than using CPU for these small networks anyways. Are you not running it on collab?

Best,
Bernie

from deep-learning-for-causal-inference.

I tried different version of tensorflow and find that tensorflow>2.10 will get the error. I use tensorflow=2.10.0 and it is fine now!

from deep-learning-for-causal-inference.