-
Notifications
You must be signed in to change notification settings - Fork 45.6k
adding implementation of https://arxiv.org/abs/1805.06066 #5265
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Thanks @arsalan-mousavian. Typically, models in the Research repository require a collaborator at Google Research to take ownership. Are you working with someone there, or do you have somebody who is willing to act as reviewer and owner of the code? |
Lovely. Thanks for letting me know. |
### TODO: SUNCG Dataset | ||
Current version of the code does not support SUNCG dataset. It can be added by | ||
implementing necessary functions of `envs/task_env.py` using the public | ||
releaseed code of SUNCG environment such as |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
released
## 3. Training | ||
Right now, the released version only supports training and inference using the real data from Active Vision Dataset. | ||
|
||
When RGB image modality is used Resnet the embedding is initialized is used To start the training download pre-trained Resnet50 check point in the working directory ./resnet_v2_50_checkpoint/resnet_v2_50.ckpt |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
seems like a typo here.
Maybe something like:
When the RGB image modality is used, the Resnet embeddings are initialized.
Addressed the comments. Please take a look. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Excellent. For my own reference, approval link:
go/cognitive_planning_oss_approval
No description provided.