dandelin ViLT issues - Githubissues

dandelin / ViLT

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

Apache License 2.0

1.41k stars 208 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

RuntimeError: Invalid pretrained config, cannot load weights. Use `pretrained=False` for random init.

#95 nameyun opened 2 months ago
0
missing file

#94 hussainafroz opened 3 months ago
0
Initial commit for 2024 VizWiz challenge

#93 harrychien1311 closed 7 months ago
0
When distributed training was performed, the program remained unresponsive

#92 mumu029 opened 10 months ago
0
ValueError: Connection error, and we cannot find the requested files in the cached path. Please try again or make sure your Internet connection is on.

#91 Spring24ch opened 10 months ago
2
requests.exceptions.MissingSchema: Invalid URL 'None': No scheme supplied. Perhaps you meant https://None?

#90 lingshen233 opened 10 months ago
0
Which python could I use

#89 Thealove opened 11 months ago
1
更改输入

#88 wzh226 opened 1 year ago
1
error: subprocess-exited-with-error

#87 My12123 opened 1 year ago
1
KeyError: 'false_image_0'

#86 Chendaqiang01 opened 1 year ago
0
ViLT on GQA

#85 keshavshivkumar opened 1 year ago
0
AttributeError: 'TracebackException' object has no attribute 'exc_traceback'

#84 liuliAI opened 1 year ago
3
cannot import name 'Final' from 'typing'

#83 lijiabad opened 1 year ago
2
What could be the reason that the model weights are not updating while finetuning?

#82 DDXDaniel opened 1 year ago
2
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

#81 jiajia95Murphy opened 1 year ago
2
Can't the weight folder be opened before the pre-training is over?

#80 yang178908 opened 1 year ago
0
fine-tuning ViLT for MLM task with a new dataset

#79 Ellyuca opened 1 year ago
0
pyarrow.lib.ArrowInvalid: Not an Arrow file

#78 ghost closed 1 year ago
2
Mistakes in vqa_dict.json ？

#77 boqian-li closed 7 months ago
0
What is the image resolution during VQA finetuning and pretraining?

#76 sanyalsunny111 opened 2 years ago
0
The problem of fine-flickr30k

#75 wuqiang12345 opened 2 years ago
0
pretrain datasets

#74 mactavish91 opened 2 years ago
0
Question about train on coco dataset

#73 Bmilab22 opened 2 years ago
1
RuntimeError: CUDA error: invalid device function

#72 lonestar234028 opened 2 years ago
3
train on coco dataset

#71 weiyutao886 opened 2 years ago
7
How to set the config to create a stand_alone commandline demo ?

#70 Ngheissari closed 2 years ago
1
About MS-COCO pre-training dataset

#69 4fee8fea opened 2 years ago
1
About SBU Caption dataset

#68 4fee8fea opened 2 years ago
1
How to use the modal-type embedding in the output of encoder?

#67 rginjapan opened 2 years ago
1
train customer data

#66 guanhdrmq opened 2 years ago
1
utils/write_<>.py: Is there any way to write to disk on the fly instead of loading the entire dataFrame into memory?

#65 zdxdsw closed 2 years ago
1
ViLT training time

#64 xii-rao opened 2 years ago
1
Why is answers set to 0 for irtr even for the positive case?

#63 TheShadow29 closed 2 years ago
3
How to use ViLT model for Spanish Text ?

#62 karndeepsingh opened 2 years ago
1
Finetune is failing ValueError: operands could not be broadcast together with shapes (384,576) (3,)

#61 amitkayal opened 2 years ago
2
Flickr30k Image and Text Retrieval - Query regarding training

#60 gchhablani opened 2 years ago
2
Waiting for localhost

#59 seifmaged31 opened 2 years ago
0
Question about GCC

#58 Sry2016 opened 2 years ago
1
AttributeError: 'LightningDistributedDataParallel' object has no attribute '_sync_params'

#57 KimSoybean opened 2 years ago
1
Checkpoint file for VQA might be wrong

#56 jia2lin3yuan1 opened 2 years ago
0
while read file idx 2740206 in conceptual_caption_train_0 -> image file is truncated

#55 campper opened 2 years ago
1
what is the meaning of "split" in /vilt/utils/write_conceptual_caption.py

#54 campper opened 2 years ago
0
Question about pad_choice

#53 Richar-Du opened 2 years ago
0
Question about ITM pretraining

#52 EagleW opened 2 years ago
0
Got better results than in the paper:

#51 JoanFM opened 2 years ago
2
integrate with Lightning ecosystem CI

#50 pl-ghost opened 2 years ago
0
COCO split for pre-training

#49 sanjayss34 opened 2 years ago
0
ITM Objectives task will not be enabled？

#48 CQUTWangHong opened 2 years ago
2
self.mask_token at 553 line in vision_transformer.py #35 I find the self.mask_token has not been defined.

#47 yr666666 opened 2 years ago
0
How to run programs on multiple machines, such as 4 machines with 8 gpus(4*8=32 in total)?

#46 raojay7 closed 2 years ago
0