salesforce/BLIP

Issues

• blip_vqa error

  #211 opened 6 months ago by AIWASS23
  1

• ITM Loss Stuck at 0.63

  #200 opened a year ago by bfan1256
  3

• FileNotFoundError: [Errno 2] No such file or directory: 'export/share/datasets/vision/coco/images/val2014/COCO_val2014_000000184613.jpg'

  #218 opened 4 months ago by Jingut
  1

• No scores of VQA evaluation

  #181 opened a year ago by p1k0pan
  5

• How to train itm from itc

  #217 opened 5 months ago by Raion-Shin
  0

• RuntimeError: Default process group has not been initialized, please make sure to call init_process_group (train_caption.py)

  #194 opened a year ago by Y-HuiMing-Y
  1

• is it possible to change the text LLM of blip to a different LLM?

  #216 opened 5 months ago by KAABSHAHID
  0

• I have created a multimodal large model technology exchange group,welcome to join us.

  #215 opened 5 months ago by feihuamantian
  0

• Caption on ImageNet-Dogs

  #214 opened 5 months ago by LouisDong95
  0

• ModuleNotFoundError: No module named 'ruamel_yaml'

  #197 opened a year ago by WenjunHuang94
  2

• knowledge distillation

  #212 opened 6 months ago by sssssshf
  0

• ERROR: Could not build wheels for tokenizers, which is required to install pyproject.toml-based projects

  #176 opened a year ago by TheOneTrueGuy
  4

• Error while running Colab demo

  #202 opened 10 months ago by staru09
  1

• The size of tensor a (3) must match the size of tensor b (9) at non-singleton dimension 0

  #165 opened 2 years ago by Peter-D-James
  18

• How to use roberta as the decoder

  #209 opened 9 months ago by xiweideng
  0

• Can BLIP generate more words image caption?

  #175 opened a year ago by uestcMeng
  7

• The rank_answer function in BLIP is different from that in ALBEF

  #208 opened 9 months ago by littleFlyDance
  0

• Question or bug in blip_pretrain.py

  #207 opened 9 months ago by LiGuo12
  0

• stable-diffusion RuntimeError: Couldn't fetch BLIP.

  #201 opened a year ago by saiheitor
  1

• How to retrive the raw attention scores or logits from blip model ( image captioning)

  #206 opened 9 months ago by umme17
  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 opened 10 months ago by shams2023
  0

• Image-Text Retrieval

  #204 opened 10 months ago by mjjc111
  0

• LAION 115M dataset has 11164.tar?

  #203 opened 10 months ago by jacob-kang
  0

• Convert BLIP model to TensorRT

  #169 opened a year ago by Frostbite22
  1

• Blip Replicate Interface Is Down

  #198 opened a year ago by hashnimo
  1

• How to use the retrival large model for image-text prediction (model_large_retrieval_coco) ?

  #199 opened a year ago by caydenwei
  0

• web demo issue

  #196 opened a year ago by hhzhao0525
  0

• I am having trouble running evaluation code

  #189 opened a year ago by jyrana
  5

• BlipForImageTextRetrieval loss returned when labels is provided

  #195 opened a year ago by AIIRLab
  0

• what's the effect of 'image_queue' and 'text_queue'

  #193 opened a year ago by FengWu-PKU
  1

• How does the BLIP model use half-precision (FP16) inference?

  #192 opened a year ago by WKaiH123
  0

• About the ViT of BLIP

  #191 opened a year ago by LWShowTime
  0

• Need clearly Understand of each checkpoint

  #190 opened a year ago by p1k0pan
  0

• 相似图像生成的caption一样，该如何解决？

  #188 opened a year ago by shams2023
  0

• 一张3090卡去微调COCO检索，需要多长时间？

  #186 opened a year ago by shams2023
  2

• Video subtitle generation

  #187 opened a year ago by Levi-arch1
  0

• The pre-trained BLIP model is used directly to perform caption operation, but the generated caption effect is not good

  #183 opened a year ago by shams2023
  0

• Questions when evaluating the finetuned BLIP model on COCO.

  #172 opened a year ago by Kaisor-Yuan
  0

• New ViT findings via registers (2309.16588)

  #184 opened a year ago by Infinitay
  0

• .

  #182 opened a year ago by shams2023
  0

• This error indicates that your module has parameters that were not used in producing loss

  #180 opened a year ago by ericosmic
  0

• Request for BLIP Pretrain Training Logs and Dataset Inquiry

  #179 opened a year ago by Aitical
  0

• demo.ipynb : RuntimeError: The size of tensor a (3) must match the size of tensor b (9) at non-singleton dimension 0

  #173 opened a year ago by Taiga10969
  6

• what is mean of 'question_states += [question_output.last_hidden_state[b]]*n'

  #178 opened a year ago by ericosmic
  0

• retrieve output not fix

  #177 opened a year ago by ltm920716
  0

• Cosine between image_features and text_features taken from BLIP_Extractor_Features gives bad results

  #174 opened a year ago by aTunass
  0

• I train on Chinese data with 5000w image-text pairs and it works.

  #170 opened a year ago by Hoogck
  0

• RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

  #168 opened a year ago by HWH-2000
  0

• Image-Text Matching result werid

  #167 opened a year ago by jucic
  0

• Issue with Tracing PyTorch Model Using torch.jit.trace

  #166 opened 2 years ago by delegatepattern
  0