Avijit Dasgupta comments

Results 32 comments of


                                            Avijit Dasgupta

Execution Error: The method 'ExecuteMso' from the object '_CommandBars' has failed

Same issue here

Investigate if lr_scheduler from segmentation can use PyTorch's schedulers

Is there any ``polynomial learning rate scheduler`` implemented yet? I can see this issue still open - https://github.com/pytorch/pytorch/issues/2854 cc: @fmassa @datumbox

I think I have figured it out. Check the `make_loss` function `per_target_loss = my_ops.mse_ignore_nans(pred_relevant, targets_preprocessed, reduction_indices=0) loss = tf.reduce_sum(per_target_loss)` That means you take mean across samples (as given in equation...