Pinned Repositories
Benchmarking-Modern-CNN-Architectures-to-RVL-CDIP
curso_jurimetria
Curso sobre jurimetria
Document-Image-Classification
The RVL-CDIP (Ryerson Vision Lab Complex Document Information Processing) dataset consists of 400,000 grayscale images in 16 classes, with 25,000 images per class. There are 320,000 training images, 40,000 validation images, and 40,000 test images.
Document-Image-Classification-with-Intra-Domain-Transfer-Learning-and-Stacked-Generalization-of-Deep
RVL-CDIP could be looked at as the equivalent of ImageNet for the document image community. It’s certainly the largest we’ve seen in the literature. There are 400,000 total document images in the dataset. The dataset contains much noise and variance in composition of each document class. Uncompressed, the dataset size is ~100GB, and comprises 16 classes of document types, with 25,000 samples per classes. Example classes include email, resume, and invoice. Achieved an Accuracy of over 93% which beat the benchmark score of 92% based on https://paperswithcode.com/sota/document-image-classification-on-rvl-cdip
Document-Structure-Classification-for-Information-Retrieval
For OCR tasks, document structure (e.g. email, letter, memo, etc.) may provide critical insight and helps to improve overall quality of the OCR task. With this use case in mind, I used the RVL-CDIP dataset to predict the structure of a document given a scanned image
DSWP
Data Sciency With Python Repo
Final-Project-Group5
Constructing Convolutional Neural Networks to train on the RVL-CDIP dataset
labelImg
🖍️ LabelImg is a graphical image annotation tool and label object bounding boxes in images
llama
Inference code for LLaMA models
poc-nfse-nacional
bwariel's Repositories
bwariel/poc-nfse-nacional
bwariel/Benchmarking-Modern-CNN-Architectures-to-RVL-CDIP
bwariel/curso_jurimetria
Curso sobre jurimetria
bwariel/Document-Image-Classification
The RVL-CDIP (Ryerson Vision Lab Complex Document Information Processing) dataset consists of 400,000 grayscale images in 16 classes, with 25,000 images per class. There are 320,000 training images, 40,000 validation images, and 40,000 test images.
bwariel/Document-Image-Classification-with-Intra-Domain-Transfer-Learning-and-Stacked-Generalization-of-Deep
RVL-CDIP could be looked at as the equivalent of ImageNet for the document image community. It’s certainly the largest we’ve seen in the literature. There are 400,000 total document images in the dataset. The dataset contains much noise and variance in composition of each document class. Uncompressed, the dataset size is ~100GB, and comprises 16 classes of document types, with 25,000 samples per classes. Example classes include email, resume, and invoice. Achieved an Accuracy of over 93% which beat the benchmark score of 92% based on https://paperswithcode.com/sota/document-image-classification-on-rvl-cdip
bwariel/Document-Structure-Classification-for-Information-Retrieval
For OCR tasks, document structure (e.g. email, letter, memo, etc.) may provide critical insight and helps to improve overall quality of the OCR task. With this use case in mind, I used the RVL-CDIP dataset to predict the structure of a document given a scanned image
bwariel/DSWP
Data Sciency With Python Repo
bwariel/Final-Project-Group5
Constructing Convolutional Neural Networks to train on the RVL-CDIP dataset
bwariel/labelImg
🖍️ LabelImg is a graphical image annotation tool and label object bounding boxes in images
bwariel/llama
Inference code for LLaMA models
bwariel/NeuralDocumentClassification
Document image classification with neural networks on a subset of the RVL-CDIP dataset.
bwariel/NF-e-Ouro-Java
Exemplo de integração com as APIs da NF-e Ouro
bwariel/NF-e-Ouro-Node.js
Exemplo de integração com as APIs da NF-e Ouro
bwariel/NF-e-Ouro-Python
Exemplo de integração com as APIs da NF-e Ouro
bwariel/NFS-e-Node.js
Exemplo de integração com as APIs da NFS-e (Nota Fiscal de Serviço eletrônica) para contribuintes e fiscos municipais
bwariel/preprocess-rvl-cdip
Preprocess the RVL-CDIP dataset into a grouped by category format
bwariel/PySimpleGUI
Launched in 2018 Actively developed and supported. Supports tkinter, Qt, WxPython, Remi (in browser). Create custom layout GUI's simply. Python 2.7 & 3 Support. 200+ Demo programs & Cookbook for rapid start. Extensive documentation. Examples using Machine Learning(GUI, OpenCV Integration, Chatterbot), Floating Desktop Widgets, Matplotlib + Pyplot integration, add GUI to command line scripts, PDF & Image Viewer. For both beginning and advanced programmers .
bwariel/PythonDataScienceHandbook
Python Data Science Handbook: full text in Jupyter Notebooks
bwariel/rvl-cdip
bwariel/RVL_IIT_mapper
This program maps the RVL-CDIP subset of dataset with the IIT CDIP dataset.
bwariel/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
bwariel/TCC_PucMinasVirtual_DataScience
Trabalho de conclusão para obtenção de título de especialista em Ciência de Dados e Big Data pela PUC Minas Virtual. Trata-se de projeto de ciência de dados em que são aplicadas técnicas de regressão linear e polinomial.
bwariel/unilm
UniLM - Unified Language Model Pre-training / Pre-training for NLP and Beyond