Turningl

Why index 1 is out of bounds for axis 0 with size 1?

1

The size of my dataset is (150, 32) and the y-label is (150, ) I don't get an error with the open source dataset on your package, but I get...

Have to admit that your package works really well, I really like the contour plots in it to see the impact of the two attribute features. I would like to...

shap.partial_dependence_plot('TPSA', model=model.predict, data=dataset, ice=False, model_expected_value=False,feature_expected_value=False, ylabel='Avg EQE') plt.tight_layout() plt.savefig('TPSA_avg_EQE.svg', dpi=1080) Hello I want to save the vector image, but the saved image is blank, why?

I know, I know. Thank you for responding to my question. What I want to ask is why you sort them like this, for example ('B', 0), ('B', -1) and ('Br', 0), ('Br', -1), ('Br', 2), etc. all start with 0 charge, then why 'I' starts with -1 charge，such as ('I', -1), ('I', 0), ('I', 1), ('I', 2), ('I', 3)?

1

I know, I know. Thank you for responding to my question. What I want to ask is why you sort them like this, for example ('B', 0), ('B', -1) and...

copy.deepcopy(model), why?

1

Hello, your project has helped me a lot. Thank you very much. But I have a question: why do I need copy.deepcopy(model) when I am trying to implement a federated...

can't install reduce

3

hello sir, I can't download reduce python package from anaconda or pip. Could you please tell me the right way to download it?

from tensorflow_privacy.privacy.analysis import privacy_ledger

3

ImportError: cannot import name 'privacy_ledger' from 'tensorflow_privacy.privacy.analysis' (C:\miniconda3\envs\tensorflow-gpu\lib\site-packages\tensorflow_privacy\privacy\analysis\__init__.py)

consult

1

Hello professor: when I run your code, I have some problem. ### Traceback (most recent call last): File "D:/Federated_learning/SpreadGNN_torch/utils/data_loader.py", line 216, in load_data(args) File "D:/Federated_learning/SpreadGNN_torch/utils/data_loader.py", line 189, in load_data train_data_local_dict[client]...