JeremyCJM

Positional Encoding

2

Why the positional encoding is random?

### 🐛 Describe the bug I am training the ViT-B16 using the reference code provided by PyTorch: [https://github.com/pytorch/vision/blob/a61e6ef6ff5af041661ecc70b1a7e3dacb2240b6/references/classification/train.py](url). However, when I resume the training using this code with the distributed...

Hi Mingyuan, Why the positional encoding of gesture sequence is a random initialized learnable tensor (self.sequence_embedding)? `h = h + self.sequence_embedding.unsqueeze(0)[:, :T, :]` Thanks, Jeremy

Multiple GPU on a single node without slurm

1

Hi Mingyuan, How to run with multiple GPUs on a single server? Thanks, Jeremy

What is "opt.times" for?

2

Hi Mingyuan, What is "opt.times" for? I see it is multiplied on the real dataset length in __len__() method, why do this? Why not just increase the epoch number? Thanks,...

What is "zero_module" for?

1

Hi Mingyuan, Why zero out the parameters of the "self.out" projection module in transformers.py? Thanks, Jeremy

Waht is "xf_proj" for?

2

Hi Mingyuan, I am wondering what is "xf_proj" for in [https://github.com/mingyuan-zhang/MotionDiffuse/blob/main/text2motion/models/transformer.py#L394](url). Why do you select the word with the maximum embedding value? Thanks, Jeremy

Why does PeriodicPositionalEncoding have a dropout?

1

Hi Evelyn, Why does PeriodicPositionalEncoding have a dropout? Thanks, Jeremy

Evaluation on My Dataset: How to Get the 251-dimensional Motion Vectors?

4

Hi Mingyuan, Do you know how to get the 251-dimensional motion vectors as provided in the KiT dataset? I am computing the FID on my dataset, but our data only...

Complete Workflow for Converting RGB Video to Event Data

8

Hi supitalp, Thanks a lot for your work! I finally installed your package successfully and got the 'out.bag' output. But I am not sure what is this output and how...