Pinned Repositories
ALPR-Yolov5
Audio-Preprocessing
# Conversion of raw audio file to readable format
CRNN_tf2
CRNN implementation in tensorflow 2
EfficientDet
f_DAGAN
Data Augmentation based on data and feature spaces
FOTS_tf_efficientnet
FOTS: Fast Oriented Text Spotting with a Unified Network implementation using EfficientNet backbone
NLP
Text-data-Augmentation
create artificial data for any kind of OCR project
video-and-image-processing
Convert video file into images using timestamp
YOLO_v3
bharatsubedi's Repositories
bharatsubedi/ALPR-Yolov5
bharatsubedi/PARseq_torch
Torch version of parseq module
bharatsubedi/FOTS_tf_efficientnet
FOTS: Fast Oriented Text Spotting with a Unified Network implementation using EfficientNet backbone
bharatsubedi/Audio-Preprocessing
# Conversion of raw audio file to readable format
bharatsubedi/EfficientDet
bharatsubedi/Text-data-Augmentation
create artificial data for any kind of OCR project
bharatsubedi/video-and-image-processing
Convert video file into images using timestamp
bharatsubedi/YOLO_v3
bharatsubedi/CRNN_tf2
CRNN implementation in tensorflow 2
bharatsubedi/f_DAGAN
Data Augmentation based on data and feature spaces
bharatsubedi/NLP
bharatsubedi/parseq
Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)