CONCH

CONCH copied to clipboard

Implementation of Image-to-Text (Captioning)

1

Hi, I was wondering if CONCH is able to directly convert an image to text? From the code, it seems like CONCH is only available for "image-to-text retrieval," meaning that...

bryanwong17

Amazing work! Congratulations! Could you share the information of what slides did you use a test set in downstream tasks? I am interested in slide-level predictions for the TCGA datasets....

PabloMeseguerEsbri

Excellent work. May I ask if you have plans to release 1.17 million image-caption pairs?

fengweie

we'd like to follow your excellent work , but can you provide your segmentation code or demo?

simzhangbest

Regarding the model's architecture, I have a question. CONCH seems to be the same as [coca](https://arxiv.org/pdf/2205.01917v2). Where exactly are their differences?

Asunatan

Hello! The paper mentioned that TCGA-NSCLC data was used for validation, which contains a total of 150 samples. Could you please provide the names of these 150 test samples?

AndrewTal

Hi, Thanks for sharing your work! Can you please also share the training setup of CONCH? I want to fine-tune CONCH so it can properly caption my H&E data. I...

Fclef

Hi! Congrat. Can you release the image-caption pairs collected from PubMed?

Elliot-QxZhang

Added correct parameter.

bhosalems

Warning when loading the model

3

Hi, I received below warning when trying to load the model. Is it okay? Thanks! conch/open_clip_custom/factory.py:18: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the...

bryanwong17