RuntimeError: Inplace update to inference tensor outside InferenceMode is not allowed.You can make a clone to get a normal tensor before doing inplace update.See https://github.com/pytorch/rfcs/pull/17 for more details.

[adrianvallsc]

When I'm running an inference on the CPU I obtain the following error. The model is being deployed on a Docker, with Ubuntu installed and pytorch 2.3.0+cu121.

The full error is this one

File "/opt/conda/bin/nnUNetv2_predict", line 8, in <module>
    sys.exit(predict_entry_point())
  File "/opt/conda/lib/python3.9/site-packages/nnunetv2/inference/predict_from_raw_data.py", line 864, in predict_entry_point
    predictor.predict_from_files(args.i, args.o, save_probabilities=args.save_probabilities,
  File "/opt/conda/lib/python3.9/site-packages/nnunetv2/inference/predict_from_raw_data.py", line 256, in predict_from_files
    return self.predict_from_data_iterator(data_iterator, save_probabilities, num_processes_segmentation_export)
  File "/opt/conda/lib/python3.9/site-packages/nnunetv2/inference/predict_from_raw_data.py", line 373, in predict_from_data_iterator
    prediction = self.predict_logits_from_preprocessed_data(data).cpu()
  File "/opt/conda/lib/python3.9/site-packages/nnunetv2/inference/predict_from_raw_data.py", line 492, in predict_logits_from_preprocessed_data
    prediction += self.predict_sliding_window_return_logits(data).to('cpu')```

I think it might be related with the last line `prediction += self.predict_sliding_window_return_logits(data).`

How can I solve the error?

[chris-rapson-formus]

This is a duplicate of #2193 (and #2364)