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
{{ message }}
This repository has been archived by the owner on Aug 28, 2021. It is now read-only.
Hello, I have been trying to implement the Gated-LSTM baseline according to the descriptions in the RoomNav paper (link), but I am confused with the some of the notations.
From Section 5.2.2 (for Gated-LSTM):
The symbol $I$ is used to denote the target instruction. This same symbol was used in Section 5.1.2 (for Gated-CNN) to denote the target instruction prior to conversion to an embedding vector $y$:
So if we were to follow the same notation as in Section 5.1.2, we would have to feed the one-hot vector $I$ (and not the embedding vector) as input to the gated fusion module and the LSTM for the Gated-LSTM.
However, the Figure 2 seems to imply that it is in fact the embedding vector that is fed into the gated fusion and the LSTM:
Could you clarify whether the target $I$ for Gated-LSTM baseline is meant to be the one-hot vector or the embedding vector?
Thank you in advance.
The text was updated successfully, but these errors were encountered:
Previously (as in minosworld/minos#94), we were able to request the authors for the SUNCG dataset.
Due to legal issues (citation), however, the download links and the forms have all been removed (c727331).
I do not think the dataset is going to be available again in a while, if at all.
Previously (as in minosworld/minos#94), we were able to request the authors for the SUNCG dataset.
Due to legal issues (citation), however, the download links and the forms have all been removed (c727331).
I do not think the dataset is going to be available again in a while, if at all.
Unfortunately, I am not aware of any download links that work anymore.
My knowledge is possibly outdated, but if house dataset/environment is what you need, you may also want to consider GibsonEnv with Matterport3D dataset.
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Hello, I have been trying to implement the Gated-LSTM baseline according to the descriptions in the RoomNav paper (link), but I am confused with the some of the notations.
From Section 5.2.2 (for Gated-LSTM):
The symbol
$I$
is used to denote the target instruction. This same symbol was used in Section 5.1.2 (for Gated-CNN) to denote the target instruction prior to conversion to an embedding vector$y$
:So if we were to follow the same notation as in Section 5.1.2, we would have to feed the one-hot vector
$I$
(and not the embedding vector) as input to the gated fusion module and the LSTM for the Gated-LSTM.However, the Figure 2 seems to imply that it is in fact the embedding vector that is fed into the gated fusion and the LSTM:
Could you clarify whether the target
$I$
for Gated-LSTM baseline is meant to be the one-hot vector or the embedding vector?Thank you in advance.
The text was updated successfully, but these errors were encountered: