Ankit Singh
Ankit Singh
@cinjon can you share the PyTorch code for THUMOS 14 that you used to reproduce the results
Ok then. Go ahead
@lavi061997 that would be great .I highly appreciate your contribution. Lets break into three different issues and solve them iteratively.
Which pretrained model you used to initialize the 3D and 2D model in YoWo architecture?
@MiaSanLei sorry to ask another question, I was using the above settings as you described but `nan` was creeping in during training. Did you change anything in ucf.yaml config file...
I am also facing the same any update on this?
ok. What I meant from more labelled data means fixed labelled data from original iteration and unlabeled data with pseudo labels (which are selected through selection criterion).
@Yu-Wu https://github.com/Yu-Wu/Exploit-Unknown-Gradually/blob/a3ebea3851ef98e32d4611250c779c84cfbde171/run.py#L75 This is where we are determining the no of samples to be selected. It doesn't seem to be equal to equation in the paper `m_t=m_t−1+p·nu` Here nu is...
ok.Thanks for quick explanation but Here `len(u_data)` is changing after each run wherein the paper `nu` is the cardinality of the INITIAL unlabeled set. Let me know if I am...
Since you are increasing the no of selection each step. Then how you deal with repeated pseudo labelled data. What I want to ask is let's say a pseudo labelled...