NielsRogge/Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
Jupyter NotebookMIT
Issues
- 2
- 2
- 8
Fine tuning SAM with multiple bounding boxes
#331 opened by mohdsaqibxa - 4
Clarification on the Nougat Transformers
#354 opened by Dipankar1997161 - 4
- 5
Inference on fine tuned LayoutLMv3 model
#324 opened by nn-Nikita - 1
Inference code for Pix2Struct on cord dataset
#363 opened by AbdulDD - 6
- 3
- 0
Urgent infenrence code for LiLT XLM-Roberta
#371 opened by mellahysf - 1
- 7
Fine-tuning Oneformer
#365 opened by nickponline - 1
- 2
recipe for finetuning OneFormer
#330 opened by werner-rammer - 0
AttributeError: 'function' object has no attribute 'items' while finetuning segment anything model
#368 opened by Snimm - 0
- 0
About the Nougat deploy?
#366 opened by CVHub520 - 4
OWLv2 with Input box image guided detection
#364 opened by theodu - 0
- 0
Multiple values error for keyword argument 'header_text' while Training Pix2Struct for the VQA task
#360 opened by Warsha-Khan - 2
- 0
- 3
Running OWLViTv2 on non-square images provides upwards shifted bounding boxes
#356 opened by Thomas-Malchers - 1
Donut finetuning RVL-CDIP ipynb -- add class names to tokenizer as empty strings?
#353 opened by plamb-viso - 0
- 2
LayoutLMv3 correct OCR engine
#352 opened by FrancescoSaverioZuppichini - 1
- 0
Finetuning Donut throws KeyError
#349 opened by tanuki0492 - 0
Upgrade Fine_tuning_DetrForObjectDetection notebook to use PyTorch Lightning with MPS support
#348 opened by plannaAlain - 0
- 2
Fine-tuning LayoutLMForSequenceClassification on RVL-CDIP.ipynb class label numbers issue
#345 opened by tompfs - 1
fine-tuning table transformer model
#346 opened by skwskwskwskw - 0
Can DINO be prompted with a pixel or image patch?
#344 opened by nickponline - 3
- 0
How do I get confidence for predictions for Label Classification using LayoutLM Models
#342 opened by piyushagarwal73 - 0
- 0
- 2
Why is 30 epochs used for LiLT finetuning?
#338 opened by 42Craft - 0
Fine tuning DiT classifier
#336 opened by aymanechilah - 2
AttributeError: 'ViltImageProcessor' object has no attribute 'pad_and_create_pixel_mask'
#335 opened by CarolineGao - 1
- 0
Model deepmind/multimodal-perceiver can't be found when working with tutorials in PerceiverForMultimodalAutoencoding
#332 opened by DjKesu - 0
.
#328 opened by AnustupOCR - 0
Fine-tune error on patch images medical dataset
#329 opened by sleeping4cat - 0
- 0
Issue while training Donut model for parsing with custom decoder and tokenizer
#326 opened by akashlp27 - 2
- 0
- 0
- 0