salesforce BLIP issues - Githubissues

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

4.84k stars 646 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

run demo on colab bug

#223 zkailinzhang opened 11 hours ago
0
Repetitive Output for All images

#222 bruceMug closed 1 week ago
0
What key design processes make BLIP have no limitations on text input length compared to CLIP?

#221 Yang-bug-star opened 1 month ago
0
How can I do inference with pretrained models rather than finetuned models

#220 Yang-bug-star opened 1 month ago
0
What does the model(**inputs, output_attentions=True) output?

#219 ZhanliangAaronWang opened 1 month ago
0
FileNotFoundError: [Errno 2] No such file or directory: 'export/share/datasets/vision/coco/images/val2014/COCO_val2014_000000184613.jpg'

#218 Jingut opened 2 months ago
1
How to train itm from itc

#217 Raion-Shin opened 3 months ago
0
is it possible to change the text LLM of blip to a different LLM?

#216 KAABSHAHID opened 3 months ago
0
Caption on ImageNet-Dogs

#214 LouisDong95 closed 1 week ago
0
fix the wrong words

#213 ArtificialZeng opened 3 months ago
2
knowledge distillation

#212 sssssshf opened 4 months ago
0
blip_vqa error

#211 AIWASS23 opened 4 months ago
2
fixed runtime device error

#210 antelopoul opened 6 months ago
0
How to use roberta as the decoder

#209 xiweideng opened 7 months ago
0
The rank_answer function in BLIP is different from that in ALBEF

#208 littleFlyDance opened 7 months ago
0
Question or bug in blip_pretrain.py

#207 LiGuo12 opened 7 months ago
0
How to retrive the raw attention scores or logits from blip model ( image captioning)

#206 umme17 opened 7 months ago
0
I want to use the existing image-text pedestrian dataset and finetune the BLIP model. Should I use pre-trained checkpoints weights or finetuned checkpoints weights?

#205 shams2023 opened 8 months ago
0
Image-Text Retrieval

#204 mjjc111 opened 8 months ago
0
LAION 115M dataset has 11164.tar?

#203 jacob-kang opened 8 months ago
0
Error while running Colab demo

#202 staru09 opened 9 months ago
1
stable-diffusion RuntimeError: Couldn't fetch BLIP.

#201 saiheitor opened 9 months ago
1
ITM Loss Stuck at 0.63

#200 bfan1256 opened 9 months ago
3
How to use the retrival large model for image-text prediction (model_large_retrieval_coco) ?

#199 caydenwei opened 9 months ago
0
Blip Replicate Interface Is Down

#198 hashnimo closed 9 months ago
1
ModuleNotFoundError: No module named 'ruamel_yaml'

#197 WenjunHuang94 opened 10 months ago
2
web demo issue

#196 hhzhao0525 opened 10 months ago
0
BlipForImageTextRetrieval loss returned when labels is provided

#195 AIIRLab opened 10 months ago
0
RuntimeError: Default process group has not been initialized, please make sure to call init_process_group (train_caption.py)

#194 Y-HuiMing-Y opened 10 months ago
1
what's the effect of 'image_queue' and 'text_queue'

#193 FengWu-PKU opened 11 months ago
1
How does the BLIP model use half-precision (FP16) inference?

#192 WKaiH123 opened 1 year ago
0
About the ViT of BLIP

#191 LWShowTime opened 1 year ago
0
Need clearly Understand of each checkpoint

#190 p1k0pan opened 1 year ago
0
I am having trouble running evaluation code

#189 jyrana closed 1 year ago
5
相似图像生成的caption一样，该如何解决？

#188 shams2023 opened 1 year ago
0
Video subtitle generation

#187 Levi-arch1 opened 1 year ago
0
一张3090卡去微调COCO检索，需要多长时间？

#186 shams2023 opened 1 year ago
2
Add auto-label guide

#185 capjamesg closed 1 month ago
2
New ViT findings via registers (2309.16588)

#184 Infinitay opened 1 year ago
0
The pre-trained BLIP model is used directly to perform caption operation, but the generated caption effect is not good

#183 shams2023 closed 1 year ago
0
.

#182 shams2023 closed 1 year ago
0
No scores of VQA evaluation

#181 p1k0pan closed 1 year ago
5
This error indicates that your module has parameters that were not used in producing loss

#180 ericosmic opened 1 year ago
0
Request for BLIP Pretrain Training Logs and Dataset Inquiry

#179 Aitical opened 1 year ago
0
what is mean of 'question_states += [question_output.last_hidden_state[b]]*n'

#178 ericosmic opened 1 year ago
0
retrieve output not fix

#177 ltm920716 opened 1 year ago
0
ERROR: Could not build wheels for tokenizers, which is required to install pyproject.toml-based projects

#176 TheOneTrueGuy opened 1 year ago
4
Can BLIP generate more words image caption?

#175 uestcMeng opened 1 year ago
7
Cosine between image_features and text_features taken from BLIP_Extractor_Features gives bad results

#174 aTunass opened 1 year ago
0
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