-
## ❓ Questions and Help
Is there any way/config I can use to task-specific pretrain the "VisualBERT pretrained on COCO" model on Hateful memes dataset? I'm assuming that MMF's model zoo does not prov…
-
## 🚀 Feature
Multimodal Alignment or Sentence Image Prediction loss for ViLBERT/VisualBERT
## Motivation
[VilBERT](https://arxiv.org/abs/1908.02265) model uses two pretraining losses. Current M…
-
### Feature request
Hi! Region to phrase alignment and natural language for visual reasoning have no AutoModels yet. @sgugger is it OK to open a PR and solve this?
### Motivation
This is an issue t…
-
### Feature request
VisualBert takes 2 main inputs: tokenized text and tokenized images.
The text tokenization can already be handled by the BertTokenizer, but the visual tokenization still has no …
-
## ❓ Questions and Help
Hi MMF developers,
I have been trying to use VisualBERT as shown in this issue #291, with Detectron2 Faster RCNN (#206) features for visual embeddings.
Here is what I …
-
## ❓ Questions and Help
Hi,
I want to use a new dataset to train VisualBERT. The scrept ["extract_features_vmb.py"](https://github.com/facebookresearch/mmf/blob/master/tools/scripts/features/extrac…
-
Hello MMF authors,
Thank you for your nice repo. I'm new to the repo and I'm literally looking for the simplest thing: I'd like to run masked language modeling inference with one of your pretraine…
-
## ❓ Questions and Help
Hi,
I'm working on the Hateful Memes project; I'm trying to use the proposed pretrained models to make predictions on a personal dataset.
I've been able to reproduce the res…
-
### System Info
Hi @LysandreJik , @NielsRogge, @sgugger,
I am working to apply [shap](https://shap.readthedocs.io/en/latest/index.html) algorithm on visualbert. I found a piece of code that run`s …
-
Hello! I am currently using this repository for evaluation of several VQA models, thank you for sharing this code.
Some large models such as MoViE+MCAN, ViLBERT and VisualBERT require heavy computa…