issues
search
salesforce
/
BLIP
PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
BSD 3-Clause "New" or "Revised" License
4.85k
stars
648
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
demo.ipynb : RuntimeError: The size of tensor a (3) must match the size of tensor b (9) at non-singleton dimension 0
#173
Taiga10969
closed
1 year ago
6
Questions when evaluating the finetuned BLIP model on COCO.
#172
Kaisor-Yuan
opened
1 year ago
0
Update med.py: Fixed the issue of BERTEncoder.forward() not returning cross-attentions when requested
#171
programmingLearner
opened
1 year ago
1
I train on Chinese data with 5000w image-text pairs and it works.
#170
Hoogck
opened
1 year ago
0
Convert BLIP model to TensorRT
#169
Frostbite22
opened
1 year ago
1
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same
#168
HWH-2000
opened
1 year ago
0
Image-Text Matching result werid
#167
jucic
closed
1 year ago
0
Issue with Tracing PyTorch Model Using torch.jit.trace
#166
ghost
opened
1 year ago
0
The size of tensor a (3) must match the size of tensor b (9) at non-singleton dimension 0
#165
Peter-D-James
opened
1 year ago
18
Pre-training with LAION
#164
aries-young
opened
1 year ago
0
Batch size for pre-training
#163
aries-young
opened
1 year ago
0
Bump transformers from 4.15.0 to 4.30.0
#162
dependabot[bot]
opened
1 year ago
0
RuntimeError: The size of tensor a (6) must match the size of tensor b (18) at non-singleton dimension 0
#161
Pengxin-Guo
closed
1 year ago
1
Update requirements.txt error by installing transformers version
#160
cobanov
opened
1 year ago
4
AMP dtype incompatibility
#159
danieltudosiu
closed
1 year ago
0
Error 'RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu) ' in line 147 of train_retrieval.py
#158
Qusijia
opened
1 year ago
1
Ruamel import is outdated
#157
derekmil
opened
1 year ago
0
Extracting attention value
#156
NamHyelin
opened
1 year ago
0
BLIP Image Captioning GradCAM?
#155
gwyong
opened
1 year ago
7
How did you deal with some extremely duplicated captions in the pretraining dataset?
#154
SCZwangxiao
opened
1 year ago
0
Can this model output Chinese image captionings?
#153
K-tang-mkv
opened
1 year ago
3
The ITM and LM loss do not converge
#152
chenyzh28
opened
1 year ago
3
Demo Google Colab not working
#151
detrin
opened
1 year ago
6
Reproduce image captioning results
#150
yxoh
opened
1 year ago
0
How to load the pre-trained BLIP model pth file into HuggingFace BLIP model?
#149
adventure2165
opened
1 year ago
1
Validation time more than the training time
#148
aman-cc
opened
1 year ago
0
About zero-shot Image-Text Retrieval
#147
rookiiiiiie
opened
1 year ago
1
About training time cost for pre-train model
#146
CZX-Yui
opened
1 year ago
0
Hello, I used Chinese data for training and found that all the results I got have the first character as "的", such as "的 里 有 一 的 男 士" and "的 山 小 上 一 的 女 人 和 一 手 子 的 人". I would like to ask if there is anything else I need to modify besides the data when training Chinese language.
#145
cjt222
opened
1 year ago
3
Add 🤗 integration
#144
NielsRogge
closed
9 months ago
1
Got 10 same words in respons.
#143
zss977-web
opened
1 year ago
1
A n error about "The size of tensor a (96) must match the size of tensor b (288) at non-singleton dimension 0"
#142
ZhenyuLiu-SYSU
opened
1 year ago
5
Visual Question Answering's confidence
#141
kosarkazemi
opened
1 year ago
2
Why convert images to cpu in BLIP
#140
itsik1
opened
1 year ago
0
Added gitignore
#139
ParisNeo
closed
1 year ago
2
Can I concat an additional vector to question_output?
#138
Nguyen-Van0405
closed
1 year ago
0
Why is there no VD(visual dialog) demo
#137
RainBowLuoCS
opened
1 year ago
1
Joshua/fashion iq
#136
JvThunder
closed
1 year ago
1
Joshua/fashion iq
#135
JvThunder
closed
1 year ago
1
Fix models.med.py for demo.ipynb
#134
gkswns3708
opened
1 year ago
1
There is error on demo.ipynb
#133
gkswns3708
opened
1 year ago
0
Why is there no model checkpoint that perform ITC+ITM+LM Loss on Coco/Flickr?
#132
linzhiqiu
closed
1 year ago
4
Captioning issues on Mac M1
#131
victorca25
opened
1 year ago
0
Confidence scores for image captions?
#130
key88sf
opened
1 year ago
2
Number of Gpus used for pre-training
#129
6Roy
opened
1 year ago
2
size mismatch for bert.embeddings.word_embeddings.weight
#128
LianghuiGuo
opened
1 year ago
1
Computing FLOPs
#127
AnaRhisT94
opened
1 year ago
0
[W C:\cb\pytorch_1000000000000\work\torch\csrc\distributed\c10d\socket.cpp:601] [c10d] The client socket has failed to connect to [DESKTOP-IBGND1Q]:54321 (system error: 10049 - The requested address is not valid in its context.).
#126
Nas-Azzam
closed
8 months ago
0
Image-text Retrieval demo not working
#125
shivangibithel
closed
1 year ago
1
Reproducing the pretrain results on COCO+VG +CC+SBU
#124
dyashuni
closed
1 year ago
7
Previous
Next