Issues
- 0
Architecture of ALBEF
#144 opened by Asaad-Pak - 0
Question about VQA test set run evaluation
#143 opened by sjqjh - 3
- 1
- 0
- 0
Simple Inference from ALBEF downloaded checkpoint
#141 opened by Asaad-Pak - 0
How to convert Tokens to ids correctly
#140 opened by nuistZPZ - 0
ValueError: Default process group has not been initialized, please make sure to call init_process_group.
#139 opened by nuistZPZ - 1
- 2
Missing key when loading fine-tuned vqa checkpoint
#101 opened by yezi-yang - 0
Multilingual Support
#137 opened by zhaoyib - 2
Zero-shot capabilities on ImageNet
#119 opened by kimihailv - 2
'/export/share
#132 opened by msamii - 2
How can I get Visual Genome ?
#129 opened by Clarioooo - 1
TypeError: '<=' not supported between instances of 'float' and 'str' ?
#128 opened by WangchukTsering - 1
About the Flickr-30k dataset
#136 opened by rhyhck - 5
TypeError: add_code_sample_docstrings() got an unexpected keyword argument "tokenizer_class"
#113 opened by dongxinfeng1 - 0
Overflow in `autocontrast_func`
#134 opened by MagnusOstertag - 2
The code for loss computation of itc is not corresponding to the original paper
#133 opened by Whisht - 0
- 0
ITC & ITM & MLM weight distribution
#130 opened by HWH-2000 - 1
- 1
utils.init_distributed_mode(args) Fail
#123 opened by crimama - 2
Question about answer ranking
#118 opened by dhansmair - 0
RefCOCO+ Fine-tuning
#127 opened by leizhu-angus - 0
refcoco on lower resolution
#125 opened by MLAlex1 - 2
change english text_encoder to other language?
#117 opened by jammyWolf - 0
About dropout and no_grad.
#124 opened by boyaom - 0
pretrain task
#122 opened by allenzg - 0
- 1
Cannot install in python3.6
#116 opened by slyviacassell - 6
support other visual grounding datasets?
#112 opened by PaulTHong - 1
NLVR2 Pretrain
#115 opened by lonestar234028 - 2
Momentum parameter
#114 opened by upccpu - 2
About finetuned checkpoint for VE
#111 opened by Transparent6 - 2
hard negative sample selection
#108 opened by mactavish91 - 1
About VQA annotations
#110 opened by simplelifetime - 0
could you add a self-attention to enhance the effect?
#109 opened by klodlee - 5
- 2
Do we need image_queue and text_queue in fine-tuning?
#106 opened by AHEADer - 2
About Dataset
#105 opened by celestialxevermore - 1
Grounding script vs retrival
#103 opened by Ngheissari - 1
Bug in the token_type_ids
#102 opened by sanyalsunny111 - 0
Question about NLVR2
#104 opened by litaohz - 1
- 0
About dataset
#99 opened by celestialxevermore - 2
About data augmentation for pretraining
#98 opened by vateye - 0
Question about Temperature Parameter
#97 opened by m2man - 4
- 1