dmusingu / lapvqa-pretrain-contrastive

huggingface.co
Total runs: 0
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: June 06 2026

Introduction of lapvqa-pretrain-contrastive

Model Details of lapvqa-pretrain-contrastive

LAPVQA — Pretrain (Contrastive)

Part of the LAPVQA collection .

Description

A ViT-L/14 vision encoder trained from scratch on MIMIC-CXR chest X-ray / report pairs using InfoNCE contrastive learning (image encoder vs. 6-layer bidirectional text encoder). The encoder is intended to be used as a frozen feature extractor for downstream CXR tasks.

Architecture
Component Detail
Vision backbone ViT-L/14, 24-layer, 1024-dim, 16-head, patch 14, 384 px
Text encoder 6-layer, 512-dim bidirectional transformer, GPT-2 vocab (50 257)
Projection Linear → 512-dim shared embedding space
Loss InfoNCE (symmetric softmax cross-entropy)
Training data MIMIC-CXR (physionet.org/content/mimic-cxr)
Epochs 50
Downstream Evaluation (frozen encoder + linear probe)
Dataset Mean AUC
NIH CXR-14 (14-class) 0.653
CheXpert-5 (5-class) 0.759
Files
File Description
encoder_final.pt Vision encoder weights at the end of training
model_best.pt Full model (encoder + text encoder) at best val loss
Usage
import torch
from lapvqa.pretrain.model import ContrastiveModel

ckpt = torch.load("encoder_final.pt", map_location="cpu")
model = ContrastiveModel()
model.vision_encoder.load_state_dict(ckpt)
model.eval()
Citation

If you use these weights please cite MIMIC-CXR:

@article{johnson2019mimic,
  title   = {MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports},
  author  = {Johnson, Alistair EW and others},
  journal = {Scientific data},
  volume  = {6}, pages = {317}, year = {2019}
}

Runs of dmusingu lapvqa-pretrain-contrastive on huggingface.co

0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About lapvqa-pretrain-contrastive huggingface.co Model

More lapvqa-pretrain-contrastive license Visit here:

https://choosealicense.com/licenses/apache-2.0

lapvqa-pretrain-contrastive huggingface.co

lapvqa-pretrain-contrastive huggingface.co is an AI model on huggingface.co that provides lapvqa-pretrain-contrastive's model effect (), which can be used instantly with this dmusingu lapvqa-pretrain-contrastive model. huggingface.co supports a free trial of the lapvqa-pretrain-contrastive model, and also provides paid use of the lapvqa-pretrain-contrastive. Support call lapvqa-pretrain-contrastive model through api, including Node.js, Python, http.

lapvqa-pretrain-contrastive huggingface.co Url

https://huggingface.co/dmusingu/lapvqa-pretrain-contrastive

dmusingu lapvqa-pretrain-contrastive online free

lapvqa-pretrain-contrastive huggingface.co is an online trial and call api platform, which integrates lapvqa-pretrain-contrastive's modeling effects, including api services, and provides a free online trial of lapvqa-pretrain-contrastive, you can try lapvqa-pretrain-contrastive online for free by clicking the link below.

dmusingu lapvqa-pretrain-contrastive online free url in huggingface.co:

https://huggingface.co/dmusingu/lapvqa-pretrain-contrastive

lapvqa-pretrain-contrastive install

lapvqa-pretrain-contrastive is an open source model from GitHub that offers a free installation service, and any user can find lapvqa-pretrain-contrastive on GitHub to install. At the same time, huggingface.co provides the effect of lapvqa-pretrain-contrastive install, users can directly use lapvqa-pretrain-contrastive installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

lapvqa-pretrain-contrastive install url in huggingface.co:

https://huggingface.co/dmusingu/lapvqa-pretrain-contrastive

Url of lapvqa-pretrain-contrastive

lapvqa-pretrain-contrastive huggingface.co Url

Provider of lapvqa-pretrain-contrastive huggingface.co

dmusingu
ORGANIZATIONS

Other API from dmusingu

huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:June 06 2026
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:June 06 2026