facebookresearch/mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
PythonNOASSERTION
Issues
- 1
Trouble installing MMF on Colab
#1322 opened by catherinening - 0
Error while installing mmf
#1327 opened by Arnavsmayan - 3
Issue with Installation - lmdb
#1238 opened by hassannaveed1997 - 0
Encounter distributed error when trainning ViLT
#1325 opened by accebet - 1
Checksum and FileNotFound errors when trying to evaluate pretrained models
#1324 opened by catherinening - 2
- 1
- 0
Error when running project with newer version
#1316 opened by kobrafarshidi - 1
Exception: process 0 terminated with signal SIGKILL
#1262 opened by Huangzhw0221 - 0
Error when installing mmf on google colab.
#1312 opened by BasselAli1 - 0
I encountered an error installing mmf
#1307 opened by joesevert - 0
Unable to run models in CPU for inference
#1310 opened by soonchangAI - 1
Error torch.distributed when running
#1309 opened by tinaboya2023 - 1
TextVQA Checksum - doesn't match and varies between models
#1308 opened by ab3308 - 1
VizWiz for M4C?
#1277 opened by arcb01 - 3
Mac M1 pip installation error
#1289 opened by Podidiving - 1
installation issues in colab example notebook
#1306 opened by bocanegrah - 6
issue with installation
#1296 opened by bocanegrah - 1
errors while running pytests .\test
#1287 opened by cokemhlee - 1
Conflicting requirements
#1300 opened by guptambergatech - 0
Manual Dataset Downloads
#1297 opened by anon110102 - 0
- 1
AttributeError: 'NoneType' object has no attribute 'dim' | Pretrained VILBert model
#1260 opened by wentaizhao - 0
- 1
Fine-tuning pretrained VILBERT on a custom dataset
#1248 opened by ir0nt0ad - 3
- 1
Loading the Hate meme dataset into MMF
#1269 opened by sharonchokuwa - 0
Memory leaked
#1268 opened by chocolate9624 - 0
Disk read and write too fast, resulting in server lag, how to reduce read and write speed
#1267 opened by frankst-debug - 0
OK-VQA knowledge base
#1265 opened by ifmaq1 - 0
Real URL
#1264 opened by liupeng0606 - 0
What is the feature extractor used for the pretrained M4C model provided for textvqa?
#1263 opened by onuriel - 0
Attention Maps
#1259 opened by shamanthak-hegde - 2
- 1
- 0
why we could use mmf_run to run the project?
#1257 opened by fengmingfeng - 0
why we could use mmf_run the project?
#1256 opened by fengmingfeng - 0
Please read & provide the following information
#1254 opened by soumyasj - 1
数据集下载页面访问不了,无法获得password
#1252 opened by Ruoyan-Zhao - 1
Can't reproduce UniT results with gradient accumulation
#1251 opened by RulinShao - 2
- 1
How the code recognizes validation set for TextVQA
#1246 opened by soonchangAI - 0
- 0
AssertionError: OKVQA requires 2 paths; one to questions and one to annotations
#1244 opened by Hao-YunDeng - 0
Textvqa Prediction on Single Image
#1242 opened - 0
After using extract_features_vmb.py to extract features, and then training with mcan, it reported the error message that the feature dimensions did not match.
#1239 opened by clearlove7-s11 - 0
KRISP:how to understand training graph network using binary cross entropy loss?
#1237 opened by xixihawokao - 0
- 0
Facing issue with checkpoint while running mmf_config to Finetune the VisualBERT model for Hateful Meme detection
#1234 opened by AnjumJ123 - 0
COCO dataset may be corrupted
#1233 opened by bouthilx