I am running a neural network over complex valued data and getting the following error:
Traceback (most recent call last):
File "/home/aclifton/rf_fp/run_training_w_evaluate.py", line 523, in <module>
run_training_pipeline(tmp_dict)
File "/home/aclifton/rf_fp/run_training_w_evaluate.py", line 229, in run_training_pipeline
outputs = rffp_model(**batch)
File "/home/aclifton/anaconda3/envs/rffp/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1151, in _call_impl
hook_result = hook(self, input, result)
File "/home/aclifton/anaconda3/envs/rffp/lib/python3.9/site-packages/wandb/wandb_torch.py", line 110, in <lambda>
lambda mod, inp, outp: parameter_log_hook(
File "/home/aclifton/anaconda3/envs/rffp/lib/python3.9/site-packages/wandb/wandb_torch.py", line 105, in parameter_log_hook
self.log_tensor_stats(data.cpu(), "parameters/" + prefix + name)
File "/home/aclifton/anaconda3/envs/rffp/lib/python3.9/site-packages/wandb/wandb_torch.py", line 221, in log_tensor_stats
tmin = flat.min().item()
RuntimeError: "min_all" not implemented for 'ComplexFloat'
I’m not quite sure what to make of it and was wondering if anyone could offer some advice? Thanks in advance for your help!