OFA-Sys/OFA issues and pull requests

#446 - pretraining error reporting in APPLE M3 pro device

Issue - State: open - Opened by zh-zhang1984 about 1 month ago

#445 - The instructions are beyond convoluted

Issue - State: open - Opened by TeKett about 1 month ago

#444 - OFA Base weight file over 800 M

Issue - State: open - Opened by naonao-beibei 3 months ago

#443 - Building wheels for collected packages: transformers install a wrong version of transformers (4.18.0) which is not compatible with sentence-transformers

Issue - State: closed - Opened by PedemonteGiacomo 3 months ago - 1 comment

#442 - The Chinese universal and OCR experience area of OFA does not match the test inference results of this model page

Issue - State: open - Opened by wang1223440313 5 months ago

#441 - Update evaluate.py

Pull Request - State: open - Opened by JJJYmmm 5 months ago

#440 - Batch to Inference

Issue - State: open - Opened by GGital 5 months ago

#439 - How can I train my own data set in an inmage description task？

Issue - State: open - Opened by fzb408 5 months ago

#438 - How to perform text infilling

Issue - State: open - Opened by oierIM 5 months ago

#437 - MuE training script

Issue - State: open - Opened by eazook10003 6 months ago

#436 - Improve finetune efficiency

Issue - State: open - Opened by sunnie-star 6 months ago

#435 - Is the code for the downstream task of detection open source?

Issue - State: open - Opened by sunnie-star 6 months ago

#434 - Question about data processing in pretrain data.

Issue - State: open - Opened by JJJYmmm 7 months ago - 1 comment

#433 - Grounded Captioning

Issue - State: open - Opened by manas6266 7 months ago

#432 - How to use OFA to complete the task of text to sql?

Issue - State: open - Opened by lllxf 7 months ago

#431 - pip install error

Issue - State: open - Opened by cactusgame 8 months ago - 1 comment

#430 - How to calculate expected time reduction rate

Issue - State: open - Opened by eazook10003 8 months ago

#429 - Pi Tuning

Issue - State: open - Opened by nikhilbhavani 9 months ago

#428 - TransformerDecoderLayer.py

Issue - State: open - Opened by sbm5761 10 months ago

#427 - How to generate a paragraph instead of one single sentence through image caption model?

Issue - State: open - Opened by GUOGUO-lab 10 months ago

#426 - Inquiry Regarding the Acquisition and Processing Details of text2phone_dict.txt

Issue - State: closed - Opened by NingJinzhong 10 months ago

#425 - How to perform multi frame detection for visual grounding tasks?

Issue - State: open - Opened by naonao-beibei 11 months ago

#424 - visual grounding task

Issue - State: open - Opened by naonao-beibei 11 months ago

#423 - Add Evaluation Code for Scene Graph Generation

Pull Request - State: open - Opened by JackCai1206 11 months ago

#422 - Can 4 A6000 GPUs support pretraining?

Issue - State: open - Opened by bad-meets-joke 12 months ago

#421 - "IndexError: list index out of range" on multiple GPU

Issue - State: open - Opened by bruceisme 12 months ago - 2 comments

#420 - Question regarding the role of max_image_size in image quantization

Issue - State: open - Opened by gpantaz 12 months ago - 2 comments

#419 - Does it support defect detection ?

Issue - State: open - Opened by monkeycc 12 months ago

#418 - low accuracy on VQAv2 test-std when reproducing prompt tuning experiments

Issue - State: open - Opened by huahuaxiaomuzhu 12 months ago - 1 comment

#417 - OFA-CN Fine-tuning Scripts

Issue - State: open - Opened by AAbathur about 1 year ago

#416 - OFA caption models on Hugging Face

Issue - State: open - Opened by Kabongosalomon about 1 year ago

#415 - file 'ocr_scene_test.tsv' missing

Issue - State: closed - Opened by TequilaSR about 1 year ago - 2 comments

#414 - import issue with metrics!

Issue - State: open - Opened by Moeinh77 about 1 year ago - 1 comment

#413 - How to use Finetuned checkpoint for Caption on COCO

Issue - State: open - Opened by Moeinh77 about 1 year ago - 1 comment

#412 - max_tgt_length is not used in data/mm_data/vqa_gen_dataset.py

Issue - State: open - Opened by yuezhao238 about 1 year ago - 1 comment

#411 - Where is the script to preprocess the own dataset

Issue - State: open - Opened by ANBAYM about 1 year ago - 1 comment

#410 - An error when train the prompt tuning model

Issue - State: closed - Opened by ANBAYM about 1 year ago

#409 - Image Classification Fine-tuning and Evaluation on Custom Dataset

Issue - State: open - Opened by varunnrao about 1 year ago - 1 comment

#408 - Regarding fine tuning for Custom VQA dataset

Issue - State: open - Opened by manas6266 about 1 year ago - 2 comments

#407 - SNLI_VE Inference Error

Issue - State: closed - Opened by Pefect96 about 1 year ago - 3 comments

#406 - Do you use teacher forcing during training? I did not find the relavant code.

Issue - State: closed - Opened by lxianl455 about 1 year ago

#405 - How to finetune the visual grounding?

Issue - State: closed - Opened by kevinfu1717 about 1 year ago

#404 - Reasons for evaluating the same content but with different results each time.

Issue - State: open - Opened by wangsy998 about 1 year ago

#403 - Update transformer version

Issue - State: open - Opened by 15091444119 about 1 year ago - 3 comments

#402 - Poor qualitative results with finetuned text-to-image generation model

Issue - State: open - Opened by mshukor about 1 year ago

#401 - How can I distinguish questions of the same image ?

Issue - State: open - Opened by JY9087 over 1 year ago

#400 - Can visual-grounding be changed to one-to-many target positioning?

Issue - State: closed - Opened by DingLing113 over 1 year ago - 1 comment

#399 - Do you have any communication groups for OFA, such as WeChat or DingTalk?

Issue - State: closed - Opened by srdfjy over 1 year ago

#398 - About the prefix tuning scripts of SNLI-VE, COCO Captions, VQA

Issue - State: open - Opened by Pefect96 over 1 year ago - 1 comment

#397 - Error about prompt tuning with stage2 finetuning

Issue - State: open - Opened by jlgao23 over 1 year ago

#396 - More details about VQModel used in OFA?

Issue - State: closed - Opened by YAOYI626 over 1 year ago - 4 comments

#395 - What is the meaning of each column is the .tsv file for vqa ?

Issue - State: open - Opened by JY9087 over 1 year ago - 1 comment

#394 - modify scripts

Pull Request - State: closed - Opened by logicwong over 1 year ago

#393 - Why only three parameters were output

Issue - State: closed - Opened by zhongfansun over 1 year ago - 1 comment

#392 - How to extract the bounding box or mask from the region described by OFA attention?

Issue - State: open - Opened by lucaswamser over 1 year ago - 1 comment

#391 - Feature/add text recognition

Pull Request - State: closed - Opened by JustinLin610 over 1 year ago

#390 - VQGAN 模型的版本

Issue - State: closed - Opened by PhoebusSi over 1 year ago - 3 comments

#389 - text image generation中文任务

Issue - State: open - Opened by zwkkk over 1 year ago

#388 - OFA-OCR识别微调的模型checkpoints有开源么

Issue - State: open - Opened by bannima over 1 year ago - 2 comments

#387 - Grounded VQA

Issue - State: open - Opened by simplelifetime over 1 year ago - 1 comment

#386 - Are <loc123> and <bin_123> the same token?

Issue - State: closed - Opened by jxu124 over 1 year ago - 1 comment

#385 - How to obtain Accuracy for Visual Grounding after running evaluation code

Issue - State: closed - Opened by makanju0la over 1 year ago - 1 comment

#384 - dimensions of encoder_attention_mask in inputs of OFADecoder

Issue - State: closed - Opened by SilyRab over 1 year ago - 1 comment

#383 - 制作VQAencoder的注意力图

Issue - State: open - Opened by JXH-2020 over 1 year ago

#382 - add_tokens for tokenizer

Issue - State: closed - Opened by SilyRab over 1 year ago - 3 comments

#381 - pip install error, why?

Issue - State: closed - Opened by greasebig over 1 year ago - 1 comment

#378 - How to set the length of generated tokens?

Issue - State: open - Opened by xcvil over 1 year ago - 1 comment

#372 - any params to constrain the `min_lens` when using `beamsearch` and `unconstrained-training` on vqa finetune and eval?

Issue - State: closed - Opened by yuezhao238 over 1 year ago

#364 - uncompressing image_gen_large_best.zip gets "bad zipfile offset"

Issue - State: open - Opened by huangrh99 over 1 year ago - 1 comment

#362 - Question about label_smoothed_cross_entropy.py

Issue - State: open - Opened by jun297 over 1 year ago - 4 comments

#361 - question about performance on Visual Grounding task when using prefix tuning

Issue - State: closed - Opened by h-ccc over 1 year ago - 9 comments

#352 - How to enable multi-gpus training?

Issue - State: closed - Opened by JulioZhao97 over 1 year ago - 4 comments

#351 - OFA-CN pre-train dataset

Issue - State: closed - Opened by jingshuangliu22 over 1 year ago - 1 comment

#350 - About finetunig on OFA-OCR

Issue - State: open - Opened by Renalyn-pan over 1 year ago - 6 comments

#344 - zero-shot multi-selection QA

Issue - State: open - Opened by 594zyc over 1 year ago - 1 comment

#330 - Question about the Visual Grounding inference result

Issue - State: open - Opened by Owen-Qin over 1 year ago - 2 comments

#307 - The IPv6 network addresses of (XX.XX.XX.XX, 8214) cannot be retrieved (gai error: -2 - Name or service not known)

Issue - State: open - Opened by Zhang815 almost 2 years ago - 8 comments

#305 - ImportError: cannot import name 'metrics' from 'fairseq' (unknown location)

Issue - State: closed - Opened by funykatebird almost 2 years ago - 4 comments

#294 - Why are all the sentences generated by image captioning the same sentence?

Issue - State: open - Opened by Swieo almost 2 years ago - 3 comments

#290 - Get raw image file for visualization examples in OFA

Issue - State: closed - Opened by 2003pro almost 2 years ago - 1 comment

#287 - Filtering pretraining data for Image Infilling

Issue - State: closed - Opened by varadgunjal almost 2 years ago - 3 comments

#286 - Multiple GPUs training error.

Issue - State: closed - Opened by flymark2010 almost 2 years ago - 4 comments

#285 - Multiple GPUs training error.

Issue - State: closed - Opened by flymark2010 almost 2 years ago - 1 comment

#282 - I would like to ask what GPU you use to run；I only have 4 P100

Issue - State: closed - Opened by Rushing-Life almost 2 years ago - 5 comments

#280 - How to add a new task？

Issue - State: closed - Opened by CCYChongyanChen almost 2 years ago - 1 comment

#275 - OOM Problem

Issue - State: closed - Opened by phellonchen almost 2 years ago - 1 comment

#273 - Attributes in Object Detection Pre-training?

Issue - State: closed - Opened by SpencerWhitehead almost 2 years ago - 1 comment

#268 - how the model perform on object detection?

Issue - State: open - Opened by Edwardmark almost 2 years ago - 5 comments

#267 - performance of caption stage2

Issue - State: closed - Opened by Tangshengku almost 2 years ago - 4 comments

#238 - OFA-huge hugging face - missing merges.txt and vocab.json

Issue - State: closed - Opened by willxxy about 2 years ago - 3 comments

#232 - package versions

Issue - State: open - Opened by xuliwalker about 2 years ago - 2 comments

#225 - ImportError: cannot import name 'TransformerEncoderLayer' from 'fairseq.modules

Issue - State: closed - Opened by Carlos25130 about 2 years ago - 7 comments

#212 - ConfigKeyError on VQA inference

Issue - State: open - Opened by Rosiekk about 2 years ago - 7 comments

#204 - Quick Question Regarding Image Captioning Loss Function

Issue - State: closed - Opened by abaybektursun about 2 years ago - 4 comments

#193 - The code for processing coco data and the fine-tuning code for object detection

Issue - State: open - Opened by songxueXS about 2 years ago - 3 comments

#166 - Slow Downloading Speed

Issue - State: closed - Opened by cliangyu about 2 years ago - 7 comments

#138 - OFA-Explainability

Issue - State: open - Opened by AI-EnabledSoftwareEngineering-AISE over 2 years ago - 13 comments

#131 - Error in fine-tuning on custom dataset

Issue - State: closed - Opened by kyleseelman over 2 years ago - 4 comments

#88 - unrecognized arguments: --warmup-ratio

Issue - State: closed - Opened by AI-EnabledSoftwareEngineering-AISE over 2 years ago - 4 comments

#72 - fine-tune ofa base model for object detection on custom dataset

Issue - State: closed - Opened by ilovecv over 2 years ago - 11 comments
Labels: help wanted

GitHub / OFA-Sys/OFA issues and pull requests