OpenGVLab / VideoMamba

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

https://arxiv.org/abs/2403.06977

OpenGVLab/VideoMamba Issues

Overfit Issue
Updated 3 days ago1
Difficulty Encountered While Fine-Tuning Model on Breakfast Dataset and Questions About Folder Structure
Closed 3 months ago9
请问能用AVA数据集训练模型吗
Updated 3 days ago1
TypeError: causal_conv1d_fwd(): incompatible function arguments. The following argument types are supported:
Closed 3 months ago3
apex==0.1的安装错误
Updated 5 days 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 17 days ago6
Self-distillation for video
Updated 22 days ago1
RuntimeError: The size of tensor a (4) must match the size of tensor b (16) at non-singleton dimension 1
Updated a month ago1
Wrong model weight
Closed a month ago1
RuntimeError: Expected B.stride(-1) == 1 to be true, but got false.
Updated a month ago4
公布录用版的论文
Updated a month 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 a month ago1
Can I use VideoMamba as a video encoder?
Updated a month ago1
Is the shape of this model's input fixed?
Updated a month ago1
Performance
Updated a month ago1
关于Different scan methods
Updated a month ago1
Error compiling objects for extension pip install -e causal-conv1d
Closed 3 months ago13
Does the current exp_zx/msrvtt/run.sh support zero shot evaluations on custom video dataset?
Updated 2 months ago1
Testing out VideoMamba srun configuration errors
Closed 2 months ago2
关于记录梯度值
Updated 2 months ago
在breakfast和somthingv2数据集训练过程中loss都出现nan
Updated 2 months ago14
About Visual Explanations
Closed 2 months ago1
Grad is NaN
Updated 2 months ago4
ValueError("arange's arguments must be of type tl.constexpr")
Updated 2 months ago1
Question about training a custom dataset based on the Video Mamba middle model
Closed 3 months ago6
How to Perform Frame-by-Frame Inference Using Videomamba
Closed 3 months ago2
Masked Pretraining section
Updated 3 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 3 months ago3
thank you very much for your exciting work, is there any code and results for videomamba to finetune on MSRVTT?
Closed 3 months ago1
The data type when evaluting the performance.
Closed 3 months ago1
Imagenet training diverges after some epochs
Closed 3 months ago10
I found an error for videoamba_pretrain.py
Closed 3 months ago4
About mamba block
Closed 3 months ago4
About SSv2 dataset
Closed 3 months ago7
Augmentation difference between tiny and small variants
Updated 3 months ago1
TypeError: Mamba.__init__() got an unexpected keyword argument 'bimamba'
Updated 3 months ago3
How to use VideoMamba as a backbone network
Updated 3 months ago6
Layernorm: No such file or directory: 'ldconfig'
Closed 3 months ago2
About SSv2 dataset
Closed 3 months ago
Something-something V2. Where to find train.csv?
Closed 4 months ago4
Disabling use of Slurm
Updated 3 months ago2
CUDA error: no kernel image is available for execution on the device Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
Closed 3 months ago2
File "/xxx/selective_scan_interface.py", line 331, in backward dx, dconv1d_weight, dconv1d_bias = causal_conv1d_cuda.causal_conv1d_bwd( RuntimeError: weight must have shape (dim, width)
Updated 3 months ago2
float division by zero
Closed 3 months ago2
Errors processing video files while pretraining with k400
Closed 3 months ago1
How to apply a VideoMamba to videos of different temporal resolutions with the pretraining?
Closed 4 months ago2
UMT_QA Usage
Closed 4 months ago1
Cost of training
Closed 4 months ago7
Loading Pretrained Model Weights for Continued Training
Closed 4 months ago
About the Mamba module
Closed 4 months ago2