You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
While training Donut on Synthetic Shift Outliers an exception occured:gradient for model/donut/p_x_given_z/mean/dense/bias:0 has numeric issue : Tensor had NaN values [[Node: quiet_donut_trainer_9/CheckNumerics_13 = CheckNumerics[T=DT_FLOAT, message="gradient for model/donut/p_x_given_z/mean/dense/bias:0 has numeric issue", _device="/job:localhost/replica:0/task:0/device:CPU:0"](quiet_donut_trainer_9/clip_by_norm_13/truediv)]]
The text was updated successfully, but these errors were encountered:
It looks like the gradients become 0, something is going wrong in the training. Setting optimizer_params = {epsilon:1e-05} in QuietDonutTrainer (increasing epsilon for AdamOptimizer) removed the error for me. But it's worth a discussion whether and how much we should improve the parameters of Donut.
* Adapt Donut to missing data
* Always use 'num_epochs', replace NaNs with 0 in RNN_EBM and LSTM_Enc_Dec
* Remove use_zero to let the detectors decide what happens with NaN's
* Lower epochs of LSTM_Enc_Dec
While training Donut on Synthetic Shift Outliers an exception occured:gradient for model/donut/p_x_given_z/mean/dense/bias:0 has numeric issue : Tensor had NaN values [[Node: quiet_donut_trainer_9/CheckNumerics_13 = CheckNumerics[T=DT_FLOAT, message="gradient for model/donut/p_x_given_z/mean/dense/bias:0 has numeric issue", _device="/job:localhost/replica:0/task:0/device:CPU:0"](quiet_donut_trainer_9/clip_by_norm_13/truediv)]]
The text was updated successfully, but these errors were encountered: