M. C.
M. C.
Hello, I am currently working with a kinematic chain represented by lists of joint indices in Python, similar to the following example: t2m_kinematic_chain = [ [0, 2, 5, 8, 11],...
I'm trying to understand the design choices made in this code. Specifically, I'm wondering why condition C is passed through a random mask and then a linear layer, while time...
Hello, I am currently working with a kinematic chain represented by lists of joint indices in Python, similar to the following example: t2m_kinematic_chain = [ [0, 2, 5, 8, 11],...
Hello, I am currently working with a kinematic chain represented by lists of joint indices in Python, similar to the following example: t2m_kinematic_chain = [ [0, 2, 5, 8, 11],...
Hello, when I run: python train.py name=humanml_trans_enc_512_4gpu_600k dataset=humanml training.eval_during_training=0 model.cond_mask_prob=0.1 guidance_param=2.5 training.overwrite=1 training.log_interval=1000 batch_size=128 training.num_steps=600000 num_workers=8 input_text=./assets/example_text_prompts.txt is_debug=0 I get this error message: ``` return module_to_run(*inputs[0], **kwargs[0]) File "/home/user/anaconda3/envs/motionfm/lib/python3.9/site-packages/torch/nn/modules/module.py", line...
I'm encountering an error while trying to execute the generate.py script with the humanml dataset. Below are the command and the parameters I used: `python generate.py dataset=humanml model_path=./pretrained/humanml_trans_enc_512/model000475000.pt input_text=./assets/example_text_prompts.txt` result:...
Hi! I noticed that MDM is now around 40 times faster, with sample generation taking just ~0.4 seconds. Amazing work! 🎉 I was wondering if you could share some insights...
I trained a model on a custom dataset with motion and text pairs, and the training completed successfully. However, when running the evaluation, it expects the finest.tar checkpoint file, which...