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
is BLIP w/ ViT-L and CapFilt-L model for image captioning exist?
#123
4thfever
opened
1 year ago
2
Update README.md
#122
eltociear
closed
1 year ago
0
The following `model_kwargs` are not used by the model: ['encoder_hidden_states', 'encoder_attention_mask']
#121
osi1880vr
opened
1 year ago
4
Hugging Face integration of `BLIP`
#120
younesbelkada
opened
1 year ago
0
Why the resize does not preserve the original aspect ratio
#119
yurymalkov
opened
1 year ago
2
performance gap in Flickr retrieval
#118
amandaluof
opened
1 year ago
3
Could you please provide your code for downloading CC3M+CC12M+SBU data from the json file you provided?
#117
asgsaeid
opened
2 years ago
4
import os
#116
robotPin
opened
2 years ago
1
Update requirements.txt
#115
AdamOswald
closed
2 years ago
5
update to a more recent version of transformers dependency
#114
jorahn
closed
2 years ago
2
Cors
#113
listofbanned
closed
2 years ago
1
Image Captioning (COCO) checkpoint
#112
lucas-ventura
closed
2 years ago
2
Pre-training with GPUS
#111
VincentWangty
opened
2 years ago
3
How to Fine-Tune BLIP on custom dataset?
#110
karndeepsingh
opened
2 years ago
2
Add fastapi endpoint
#109
listofbanned
closed
2 years ago
1
When I am trying to do Pretraining for custom dataset I am getting this error ,In this i am just using two images and two captions
#108
Gokul14092001
opened
2 years ago
1
When I am trying to do Pretraining using the pretraining dataset given in the repo I am getting this error
#107
Gokul14092001
opened
2 years ago
0
Why pretrained weights are bigger than finetune weights?
#106
eeyrw
closed
2 years ago
2
BLIP stopped working!
#105
MalumaDev
closed
2 years ago
1
Effective Batchsize NLVR2
#104
BennoKrojer
closed
2 years ago
0
Upgrade to Cog version 0.1
#103
chenxwh
opened
2 years ago
1
About pre-training data
#102
PeideChi
closed
2 years ago
0
assert self.queue_size % batch_size == 0 # for simplicity
#101
scarydemon2
closed
2 years ago
3
Is the LM better than MLM?
#100
SKBL5694
opened
2 years ago
3
Weird caption for a picture of flower
#99
phelogges
opened
2 years ago
5
Some doubts about weights
#98
SKBL5694
opened
2 years ago
2
Slow caption Generation
#97
FayzulSaimun
opened
2 years ago
0
which checkpoint is used for the caption in the demo display
#96
catherinezll95
opened
2 years ago
1
Question about COCO, SBU, CC3M datasets
#95
4fee8fea
opened
2 years ago
1
checkpoints of captioner and filter
#94
byougert
opened
2 years ago
0
weights sharing between the encoder and the decoder
#93
byougert
closed
2 years ago
1
How to generate more than 1 caption for an image using pretrained model
#92
RajatAayushJha
opened
2 years ago
1
Finetune vqa by own data
#91
SKBL5694
opened
2 years ago
2
some unknown error during run "train_retrieval.py "
#90
SKBL5694
closed
2 years ago
3
Do you try continuous bootstrapping?
#89
TheShadow29
opened
2 years ago
1
Paragraph captioning
#88
AnaRhisT94
opened
2 years ago
1
NoCaps test results much lower than reported val results
#87
YovaKem
closed
2 years ago
1
Filter and Captioner
#86
baolp
closed
2 years ago
3
version check
#85
RulinShao
closed
2 years ago
1
Is the checkpoint you provided for finetune pretrained with 14M or 129M data?
#84
hhzb123
opened
2 years ago
0
Pretrained Network
#83
12sf12
opened
2 years ago
1
Demo of I2T Retrival
#82
cliangyu
opened
2 years ago
1
Checkpoint Function Backward.forward: expected Tensor or tuple of Tensor (got tuple) for return value 1
#81
cdqncn
opened
2 years ago
0
visualize BLIP attention
#80
nikky4D
closed
2 years ago
5
Details about Visual-genome Dataset
#79
FingerRec
closed
2 years ago
2
Can I ask more than 1 question simultaneously through the blip_vqa model?
#78
SKBL5694
closed
2 years ago
6
Continuously increasing RAM with Pre-training
#77
abhisheksgumadi
opened
2 years ago
12
Runtime error regarding sum of probabilities
#76
abhisheksgumadi
closed
2 years ago
4
About VisDial dataset
#75
SYSU-lulc
closed
2 years ago
0
Is there any plan for the code released for the VisDial task?
#74
SYSU-lulc
closed
2 years ago
2
Previous
Next