a  dV @sddlmZmZddlZddlmZddlmZeeeeeefdddZdeeeefe ed d d Z deee eed ddZ dS))TupleUnionN)Tensor)_check_same_shape)predstarget num_outputsreturncCsRt|||dkr&|d}|d}||}tj||dd}|jd}||fS)aUpdate and returns variables required to compute Mean Squared Error. Check for same shape of input tensors. Args: preds: Predicted tensor target: Ground truth tensor num_outputs: Number of outputs in multioutput setting r)Zdim)rviewtorchsumshape)rrrdiffsum_squared_errorn_obsro/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/functional/regression/mse.py_mean_squared_error_updates    rT)rrsquaredr cCs|r ||St||S)aCompute Mean Squared Error. Args: sum_squared_error: Sum of square of errors over all observations n_obs: Number of predictions or observations squared: Returns RMSE value if set to False. Example: >>> preds = torch.tensor([0., 1, 2, 3]) >>> target = torch.tensor([0., 1, 2, 2]) >>> sum_squared_error, n_obs = _mean_squared_error_update(preds, target, num_outputs=1) >>> _mean_squared_error_compute(sum_squared_error, n_obs) tensor(0.2500) )r sqrt)rrrrrr_mean_squared_error_compute+srr )rrrrr cCs t|||d\}}t|||dS)aCompute mean squared error. Args: preds: estimated labels target: ground truth labels squared: returns RMSE value if set to False num_outputs: Number of outputs in multioutput setting Return: Tensor with MSE Example: >>> from torchmetrics.functional.regression import mean_squared_error >>> x = torch.tensor([0., 1, 2, 3]) >>> y = torch.tensor([0., 1, 2, 2]) >>> mean_squared_error(x, y) tensor(0.2500) )r)r)rr)rrrrrrrrrmean_squared_error>sr)T)Tr ) typingrrr rZtorchmetrics.utilities.checksrintrboolrrrrrrs