Imola Fodor

Last seen: ein Tag vor | Aktiv seit 2022

Followers: 0 Following: 0

Frage

How to format sequences to store in experience buffer for DRQN?
For DRQN (Deep Recurrent Q Learning) in POMDP it is needed to store entire sequences instead of individual transitions in the re...

etwa 2 Monate vor | 0 Antworten | 0

Antworten

Frage

Forward function with frozen batch normalization layers
In my application i have both batch normalization and dropout, and i would like to perform MC dropout with the forward function,...

etwa 2 Monate vor | 1 Antwort | 0

Antwort

Frage

Streamlining of zeroing out last 2 bits of fixed 16 bit number?
Would setting correctly the parameters of quantizer object be the solution when the goal is to perform bit truncation of fixed 1...

6 Monate vor | 2 Antworten | 0

Antworten

Beantwortet
CNN-LSTM validation data underperforming compared to training data
i had a similar problem, and it was because generating a particular spectrogram within a parfor loop and in a for loop give diff...

etwa 2 Jahre vor | 1

Thankful Level 1