DiffVQA head trained on the frozen
LAPVQA captioning-pretrained encoder
(
lapvqa-pretrain-captioning
).
Checkpoint is a plain
DiffVQAHead
state dict (vis_dim=1024).
Results (test set)
BLEU-4
ROUGE-2
RadGraph-s
BERTScore F1
0.468
0.562
0.303
0.938
Loading
import torch
from lapvqa.diffvqa.model import DiffVQAHead
ckpt = torch.load("pretrain-captioning_best.pt", map_location="cpu")
head = DiffVQAHead(vis_dim=1024)
head.load_state_dict(ckpt)
head.eval()
# pair with encoder_final.pt from lapvqa-pretrain-captioning
Runs of dmusingu lapvqa-diffvqa-pretrain-captioning 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-diffvqa-pretrain-captioning huggingface.co Model
More lapvqa-diffvqa-pretrain-captioning license Visit here:
lapvqa-diffvqa-pretrain-captioning huggingface.co is an AI model on huggingface.co that provides lapvqa-diffvqa-pretrain-captioning's model effect (), which can be used instantly with this dmusingu lapvqa-diffvqa-pretrain-captioning model. huggingface.co supports a free trial of the lapvqa-diffvqa-pretrain-captioning model, and also provides paid use of the lapvqa-diffvqa-pretrain-captioning. Support call lapvqa-diffvqa-pretrain-captioning model through api, including Node.js, Python, http.
lapvqa-diffvqa-pretrain-captioning huggingface.co is an online trial and call api platform, which integrates lapvqa-diffvqa-pretrain-captioning's modeling effects, including api services, and provides a free online trial of lapvqa-diffvqa-pretrain-captioning, you can try lapvqa-diffvqa-pretrain-captioning online for free by clicking the link below.
dmusingu lapvqa-diffvqa-pretrain-captioning online free url in huggingface.co:
lapvqa-diffvqa-pretrain-captioning is an open source model from GitHub that offers a free installation service, and any user can find lapvqa-diffvqa-pretrain-captioning on GitHub to install. At the same time, huggingface.co provides the effect of lapvqa-diffvqa-pretrain-captioning install, users can directly use lapvqa-diffvqa-pretrain-captioning installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
lapvqa-diffvqa-pretrain-captioning install url in huggingface.co: