Pate test specify type

[gmuraru]

Tested Pysyft with torch nightly and found this problem.
The PR can be checked out here.
The problem I had is:

  def test_torch_ref_match():
    
        # Verify if the torch implementation values match the original Numpy implementation.
    
        num_teachers, num_examples, num_labels = (100, 50, 10)
        preds = (np.random.rand(num_teachers, num_examples) * num_labels).astype(int)  # fake preds
    
        indices = (np.random.rand(num_examples) * num_labels).astype(int)  # true answers
    
        preds[:, 0:10] *= 0
    
        data_dep_eps, data_ind_eps = pate.perform_analysis_torch(
            preds, indices, noise_eps=0.1, delta=1e-5
        )
    
        data_dep_eps_ref, data_ind_eps_ref = pate.perform_analysis(
            preds, indices, noise_eps=0.1, delta=1e-5
        )
    
>       assert torch.isclose(data_dep_eps, torch.tensor(data_dep_eps_ref))
E       RuntimeError: Float did not match Double