Closed chmxu closed 2 years ago
Adding tf.compat.v1.disable_eager_execution()
to the beginning of main()
solves this error but I don't know if this is appropriate.
Hi, we were using tensorflow 1.15.0 with cuda 10.1 and I think this error is probably caused by using higher version of tensorflow. Did you get similar results in your setting? Or you can lower the tensorflow version. This should work.
Yes I can reproduce the result. Thank you!
Hi, thanks for your code! When I try to run
test_extractor_pa.py
after installing meta-dataset, I get the following error in L61.*** RuntimeError: The Session graph is empty. Add operations to the graph before calling run().
I'm using tensorflow 2.8.0, pytorch 1.9.0 and cuda 11.1. I wonder if you can help me on this problem. Thank you!