Pytorch implementation of the models RT-1-X and RT-2-X from the paper: "Open X-Embodiment: Robotic Learning Datasets and RT-X Models"
Here we implement both model architectures, RTX-1 and RTX-2
- Lucidrains
- Agorians
pip install rtx-torch
- RTX1 Usage takes in text and videos
import torch
from rtx.rtx1 import RTX1
model = RTX1()
video = torch.randn(2, 3, 6, 224, 224)
instructions = ["bring me that apple sitting on the table", "please pass the butter"]
# compute the train logits
train_logits = model.train(video, instructions)
# set the model to evaluation mode
model.model.eval()
# compute the eval logits with a conditional scale of 3
eval_logits = model.run(video, instructions, cond_scale=3.0)
print(eval_logits.shape)
- RTX-2 takes in images and text and interleaves them to form multi-modal sentences:
import torch
from rtx import RTX2
# usage
img = torch.randn(1, 3, 256, 256)
text = torch.randint(0, 20000, (1, 1024))
model = RTX2()
output = model(img, text)
print(output)
MIT
- Integrate Efficient net with RT-1 and RT-2
- create training script for both models
- Provide a table of all the datasets