LAVIS

LAVIS copied to clipboard

RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the sam

5

Regarding **blip2_feature_extraction.ipynb** found in: [https://github.com/salesforce/LAVIS/blob/main/examples/blip2_feature_extraction.ipynb](https://github.com/salesforce/LAVIS/blob/main/examples/blip2_feature_extraction.ipynb) When running on CPU it works fine, but on GPU I'm getting this error: `RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the...

AnaRhisT94

Can you release the code for zero-shot VQAv2 using OPT model? Or can you release the config file for this?

waxnkw

fix blip2_feature_extraction issue 119

4

fix issue https://github.com/salesforce/LAVIS/issues/119 to extract blip2 feature 

linbojin

BLIP2 process batch of text for image-text matching

2

Hi, **Following the example here**: https://github.com/salesforce/LAVIS/blob/main/examples/blip2_image_text_matching.ipynb How can I use `self.text_processors["eval"](text)` to process a batch of text without writing a for loop? Previous BLIP has it and was curious if...

AnaRhisT94

Prompt for BLIP2 OPT VQA

4

Hi @LiJunnan1992 and @dxli94, thanks for the great work! Do you have examples of the prompts you found to work well with the OPT version of BLIP2 for VQA? I...

codezakh

add an example for text retrieval

1

hello, Use BLIP to encode each picture and description, and then use text to encode some keywords, and recall words related to pictures and texts from keywords.

xcxhy

Question regarding the training device

1

I am confused about this single machine, because it seems that there is no such single machine with 16xA100 GPUs and guessing it is a typo.. Are you using 2...

Nyquist0

Error when always using model in cpu

1

https://github.com/salesforce/LAVIS/blob/3ac397aa075c3e60b9521b012dda3660e3e35f1e/lavis/runners/runner_base.py#L80 Hello, I get `self.model` is None when I set 'cpu' as my device. I find that if my device is 'cpu', it won't move the model to device and...

Jack-ZC8

BLIP2

1

It's a good work and I 'am very interesting to have a study. Can you provide the code? I do not find the code. thanks.

cm-xcju

How to fix this errors ? sd-webui-blip2

1

Traceback (most recent call last): File "C:\SD\venv\lib\site-packages\gradio\routes.py", line 337, in run_predict output = await app.get_blocks().process_api( File "C:\SD\venv\lib\site-packages\gradio\blocks.py", line 1015, in process_api result = await self.call_function( File "C:\SD\venv\lib\site-packages\gradio\blocks.py", line 833, in...

oaefou