issues
search
invictus717
/
MetaTransformer
Meta-Transformer for Unified Multimodal Learning
https://arxiv.org/abs/2307.10802
Apache License 2.0
1.52k
stars
114
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Issues about Image Classification
#73
Lelucermaire111
closed
2 weeks ago
6
about Modality-Agnostic Models
#72
regainOWO
closed
2 months ago
3
Can Meta-Transformer perform similar information retrieval to ImageBind?
#71
duguyue100
closed
2 months ago
3
Audio
#70
bjut-chunxiwang
closed
5 months ago
4
Pre-trained weights for Data2Seq
#69
vittoriopipoli
opened
5 months ago
1
Question in concating the features
#68
memesoo99
opened
6 months ago
0
Data2Seq for point cloud modality
#67
yozoral
closed
8 months ago
1
Data2Seq中的Vedio.py有问题
#66
li-pengcheng
closed
8 months ago
1
meta-transformer能否进行三维CT或者核磁数据的分割和检测？
#65
li-pengcheng
closed
9 months ago
2
图片格式转换(B,C,H,W)
#64
CQU1213
closed
10 months ago
1
使用metatransformer训练自己的数据集
#63
CQU1213
closed
10 months ago
1
下游任务的代码
#62
CQU1213
closed
11 months ago
1
Amount of embeddings
#61
vzapylikhin
closed
11 months ago
1
I have a question in the learning process.
#60
YooSungHyun
closed
11 months ago
1
requirements
#59
anas2908
closed
1 year ago
2
Hardware configurations for fine-tuning?
#58
tctco
closed
1 year ago
1
fix python version setting in Image/environment.yaml for MultiScaleDeformableAttention package
#57
chuxiuhong
closed
1 year ago
0
运行环境配置说明
#56
jinpeifei2015
closed
1 year ago
1
请问使用 Data2seq的 tokenizer 时输入数据的格式
#55
Zoew420
closed
1 year ago
1
Data2Seq > Hyper_Spectrum.py update from self.cls_tokens to self.cls_token
#54
jawhster
closed
1 year ago
1
为什么训练图像会出现这种错误
#53
CQU1213
closed
1 year ago
4
Explain please
#52
vzapylikhin
closed
1 year ago
2
Questions about experiments
#51
yangbang18
closed
1 year ago
1
video
#50
Darcy0218
closed
1 year ago
5
Question about the ``pretrain-finetune'' pipeline
#49
yangbang18
closed
1 year ago
5
Video
#48
Darcy0218
closed
1 year ago
2
关于text模态的使用
#47
1223haohao
closed
1 year ago
1
video
#46
Darcy0218
closed
1 year ago
1
audio
#45
Darcy0218
closed
1 year ago
1
如何使用较大版本的模型。
#44
1223haohao
closed
1 year ago
1
paper
#43
caodonghui426
closed
1 year ago
1
How to compute similarity score between different modalities?
#42
alparius
closed
1 year ago
2
how to use it?
#41
vzapylikhin
closed
1 year ago
4
Data2Seq Usage/Embedding Dim
#40
s4lome
closed
1 year ago
5
Fixed the bug of model test.
#39
Lum1104
closed
1 year ago
0
data2seq
#38
LH019
closed
1 year ago
3
audio
#37
Darcy0218
closed
1 year ago
3
audio
#36
Darcy0218
closed
1 year ago
2
How to pretrain Unified Multimodal Model?
#35
bbbdbbb
closed
1 year ago
1
Enquiry of the training code of the Unified Multimodal Model
#34
Lum1104
closed
1 year ago
1
audio问题
#33
Darcy0218
closed
1 year ago
3
Is the model that each task will have a corresponding downstream HEAD MLP?
#32
moonriver0922
closed
1 year ago
2
FileNotFoundError: [Errno 2] No such file or directory: 'Meta-Transformer_base_patch16_encoder.pth'
#31
Eachen11
closed
1 year ago
3
how to export to Onnx model for faster inference
#30
eisneim
closed
1 year ago
2
Whether to support BBOX data？
#29
nanfengguli
closed
1 year ago
5
Multiple modals
#28
HaibiaoXuan
closed
1 year ago
3
audio模块代码报错
#27
Darcy0218
closed
1 year ago
2
demo use
#26
Zhudogsi
closed
1 year ago
2
Replicating training?
#25
yhyu13
closed
1 year ago
1
what if it not use the LAION-2B dataset CLIP backbone
#24
Dongshengjiang
closed
1 year ago
1
Next