Rt1-VIT-bert #14
Open
Rt1-VIT-bert #14
+1,835
−21
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sebbyjp
requested changes
Jun 10, 2024
There was a problem hiding this comment.
motion is the correct folder name
There was a problem hiding this comment.
We only need this, vit, tokenizers, and learner
| "cuda" if torch.cuda.is_available() else "cpu" | ||
| ) | ||
| model_name = 'bert-base-uncased' | ||
| self.tokenizer = BertTokenizer.from_pretrained(model_name) |
There was a problem hiding this comment.
dont reinitialize every call
There was a problem hiding this comment.
This call is in the constructor / __init__ method. So its only initialized once when we create the Rt1Agent object
There was a problem hiding this comment.
observation, action, history size, image size should not be hard coded, use the current ones in the file as default values in case the config doesn't specify them.
| from mbodied_agents.types.controls import Motion | ||
|
|
||
|
|
||
| class MotorAgent(ABC): |
nqyy
force-pushed
the
main
branch
3 times, most recently
from
b560b84
to
1a6af9c
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Changed EfficientNet to ViT and Integrated BERT Text Encoder for
rt1Description
This update replaces the existing EfficientNet model with a Vision Transformer (ViT) and integrates a BERT text encoder for
rt1. The current implementation includes a dummy sample to test the network functionality. The training part is not included in this update.Summary:
How Has This Been Tested?
The changes have been verified by running a dummy sample to ensure the network functionality works as expected.
Testing:
Checklist