zinengtang/TVLT
PyTorch code for “TVLT: Textless Vision-Language Transformer” (NeurIPS 2022 Oral)
Jupyter NotebookMIT
Issues
- 0
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
#17 opened by saransh03sharma - 0
- 0
VQAv2 finetuned checkpoint
#15 opened by farisalasmary - 0
Finetuning for the custom dataset
#14 opened by palashmoon - 0
about mosei
#13 opened by LM-MSA - 4
The question for cmumosei.
#6 opened by AIXiaoBaiDemon - 0
- 5
- 1
Draw false video from batch
#11 opened by G-JWLee - 3
inaccurate VQA score
#10 opened by Park-ing-lot - 4
Finetuning on MOSEI but with nan output
#8 opened by BDHU - 3
- 2
CUDA memory error
#7 opened by Park-ing-lot - 8
Processing cmumosei dataset
#3 opened by BDHU - 7
Downstream task Cosine scheduler
#4 opened by G-JWLee - 1
CMU-MOSEI valid test
#2 opened by dori2063