OpenGVLab / VideoMamba

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding

https://arxiv.org/abs/2403.06977

OpenGVLab/VideoMamba Issues

Error "causal_conv1d_fwd(): incompatible function arguments"
Updated 19 hours ago2
ValueError("arange's arguments must be of type tl.constexpr")
Updated 2 days ago5
train a new model
Updated 2 days ago1
请问cu124如何安装环境？
Updated 2 days ago1
"too many values to unpack" error in mamba_ssm
Closed 9 days ago
在breakfast和somthingv2数据集训练过程中loss都出现nan
Updated 16 days ago15
About different Scan Methods Implementation
Updated 16 days ago
Self-distillation for video
Updated 18 days ago2
执行预训练文件run_videomamba_pretraining.py一直报错，提示got an unexpected keyword argument 'checkpoint_num'
Updated 2 months ago
Details on pretrained models for downstream tasks (K400).
Updated 2 months ago1
Is fvcore used to calculate computational costs（FLOPs）?
Updated 2 months ago1
如何加载imagenet1k的预训练权重？
Updated 2 months ago1
Evaluation of video_sm using trained weights
Updated 2 months ago1
Can I use VideoMamba in other video AI tasks?
Updated 2 months ago1
MultiModal pretraining issues
Updated 2 months ago3
self-distillation strategy
Updated 2 months ago1
msvd json file for evaluation
Updated 2 months ago1
Ask for prompt to generate cartoon characters of videomamba
Closed 3 months ago2
What are the training duration and GPU requirements like?
Updated 3 months ago1
Masked pretraining for the tiny or small model variants?
Closed 3 months ago8
How to achieve the temporal-first scan and spatialtemporal scan v1 & v2?
Updated 3 months ago1
mamba2 support?
Updated 3 months ago1
Can I use VideoMamba as a video encoder?
Updated 3 months ago3
_init__() got an unexpected keyword argument 'pretrained_cfg'
Closed 3 months ago
未设置独立测试集时，训练的验证集最佳结果与最终测试结果不一致，这是由于训练参数设置问题吗？
Closed 3 months ago4
Low Performance on Breakfast dataset
Closed 3 months ago6
Overfit Issue
Updated 3 months ago1
请问能用AVA数据集训练模型吗
Updated 3 months ago1
apex==0.1的安装错误
Updated 3 months ago5
IndexError: The shape of the mask [1, 1568] at index 1 does not match the shape of the indexed tensor [1, 1569, 576] at index 1
Closed 4 months ago6
RuntimeError: The size of tensor a (4) must match the size of tensor b (16) at non-singleton dimension 1
Updated 4 months ago1
Wrong model weight
Closed 4 months ago1
RuntimeError: Expected B.stride(-1) == 1 to be true, but got false.
Updated 4 months ago4
公布录用版的论文
Updated 4 months ago1
请问LUV相关的模型模型何时公开，以及regression任务的结果和模型可以公开吗
Updated 4 months ago1
Is the shape of this model's input fixed?
Updated 5 months ago1
Performance
Updated 5 months ago1
关于Different scan methods
Updated 5 months ago1
Does the current exp_zx/msrvtt/run.sh support zero shot evaluations on custom video dataset?
Updated 5 months ago1
Testing out VideoMamba srun configuration errors
Closed 5 months ago2
关于记录梯度值
Updated 5 months ago
About Visual Explanations
Closed 6 months ago1
Question about training a custom dataset based on the Video Mamba middle model
Closed 6 months ago6
How to Perform Frame-by-Frame Inference Using Videomamba
Closed 6 months ago2
Masked Pretraining section
Updated 6 months ago2
video_sm中.sh文件只有mask pretrain的，想知道在imagenet上有监督预训练的话有.sh文件吗
Updated 6 months ago3
The data type when evaluting the performance.
Closed 6 months ago1
About mamba block
Closed 6 months ago4
About SSv2 dataset
Closed 6 months ago7
Augmentation difference between tiny and small variants
Updated 6 months ago1