-
## Environment info
- `transformers` version: 4.8.2
- Platform: Linux-4.15.0-143-generic-x86_64-with-glibc2.10
- Python version: 3.8.5
- PyTorch version (GPU?): 1.7.1 (True)
- Tensorflow versio…
-
Hi,
I am using the visualbert model as shown in [visualbert visualreasoning](https://huggingface.co/transformers/model_doc/visual_bert.html#visualbertforvisualreasoning)
```
# Assumption: `get_visu…
-
I want to know about the visual token dimension.
linguistic token dimension is 768 which is same with BERT in NLP,
how about visual token?
is there a FCN for visual feature to embedding dimenstio…
-
Dear @hila-chefer ,
Thank you for releasing this repo of your fascinating work!!
Would you mind clarifying these two questions about your results for me? :)
1. Were you doing Detection or Seg…
-
I am using the [VisualBert](https://github.com/huggingface/transformers/blob/master/src/transformers/models/visual_bert/modeling_visual_bert.py) model and the [FlaxBert](https://github.com/huggingface…
-
Hi, I have trained the fine-tuned visualbert model on VQA following the instructions in the readme. But I have no idea how to make predictions on the official VQA v2.0 test-dev set and compute the ac…
-
Hi, I am running the experiments on VCR following the instructions in the readme. I have installed the customed torchvision and detectron modules. However, when the COCO pre-training process begins, …
-
Hi, I'm very interested in your work. I'd like to ask how the prediction sentence and image matching of the pre-training task are carried out？Is it in ‘TrainVisualBERTObjective’?I don't quite understa…
-
Hi,
I'm having some troubles running the code. I created a bash script as shown in the readme, but I continue getting this :
Traceback (most recent call last):
File "train.py", line 23, in
…
-
## ❓ Questions and Help
Hi, I trained VisualBERT for 6 h, stopped it, and would like to resume the model. I found the checkpoint is saved in the mmf/save/models and the latest model is "model_21000.c…