willxxy

Hello, I am aware that the augmented dataset from RobotHow can only be executed with version 1.0. However, I wanted to have the capability of adding characters in version 1.0....

Hi, thanks for the great implementation. I am currently working with greyscale images and implemented the loss for 1 channel images [here](https://github.com/willxxy/MS-SSIM-L1-For-1D/blob/main/msssim_l1.py). Would you mind looking at the implementation and...

Hello, Thank you for the wonderful work. I couldn't seem to find the function for visualizing the decoder cross attention map as shown in the paper. Would you be able...

For vh_env.py, I see that reset(self, state) function only takes one argument however in the example you provide you have this function. ``` s = env.reset(state_path , task_goals) ``` Is...

ValueError invalid values

1

I get the following error when I run train.py script. ``` File "scripts/train.py", line 256, in train_go1(headless=False) File "scripts/train.py", line 216, in train_go1 runner.learn(num_learning_iterations=100000, init_at_random_ep_len=True, eval_freq=100) File "/data/william/walk-these-ways/go1_gym_learn/ppo_cse/__init__.py", line 204,...

Hello, Thank you for the great work. I was curious on when the 13B pretrained checkpoint will be released? Thank you

Hello, Thank you for the great work. I was wondering if the code for visualizing the latent dim like the attached picture is available.

Hello, thanks for the great work. I was wondering if you could point me to the code where you apply the perturbations for image to text (especially the geometric one)....