TextBPN

Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection； Accepted by ICCV2021.

Note: The complete code (including training and testing) will be released in TextBPN V2. Relevant work is advancing, and those who are interested in our work can pay more attention to the updates here.

1.Prerequisites t

python 3.9;
PyTorch 1.7.0;
Numpy >=1.2.0
CUDA 11.1;
GCC >=10.0;
NVIDIA GPU(with 11G or larger GPU memory for inference);

2.Dataset Links

3.Models

Total-Text model (pretrained on ICDAR2017-MLT)
CTW-1500 model (pretrained on ICDAR2017-MLT)
MSRA-TD500 model (pretrained on ICDAR2017-MLT)

4.Running Evaluation

run:

sh eval.sh

The details are as follows:

#!/bin/bash
##################### Total-Text ###################################
# test_size=[640,1024]--cfglib/option
CUDA_LAUNCH_BLOCKING=1 python eval_textBPN.py --exp_name Totaltext --checkepoch 390 --dis_threshold 0.3 --cls_threshold 0.825 --test_size 640 1024 --gpu 1

###################### CTW-1500 ####################################
# test_size=[640,1024]--cfglib/option
# CUDA_LAUNCH_BLOCKING=1 python eval_textBPN.py --exp_name Ctw1500 --checkepoch 560 --dis_threshold 0.3 --cls_threshold 0.8 --test_size 640 1024 --gpu 1

#################### MSRA-TD500 ######################################
# test_size=[640,1024]--cfglib/option
#CUDA_LAUNCH_BLOCKING=1 python eval_textBPN.py --exp_name TD500 --checkepoch 680 --dis_threshold 0.3 --cls_threshold 0.925 --test_size 640 1024 --gpu 1

TextBPN Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection

Related tags

Overview

TextBPN

1.Prerequisites t

2.Dataset Links

3.Models

4.Running Evaluation

5.Experiments results

Owner

S.X.Zhang

Shape Matching of Real 3D Object Data to Synthetic 3D CADs (3DV project @ ETHZ)

A simple root calculater for python

Objax Apache-2Objax (🥉19 · ⭐ 580) - Objax is a machine learning framework that provides an Object.. Apache-2 jax

PyTorch code for our paper "Gated Multiple Feedback Network for Image Super-Resolution" (BMVC2019)

Testability-Aware Low Power Controller Design with Evolutionary Learning, ITC2021

Pytorch implementation of the paper: "A Unified Framework for Separating Superimposed Images", in CVPR 2020.

NLU Dataset Diagnostics

Code for ICLR2018 paper: Improving GAN Training via Binarized Representation Entropy (BRE) Regularization - Y. Cao · W Ding · Y.C. Lui · R. Huang

RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality?

A knowledge base construction engine for richly formatted data

pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"

Point Cloud Registration using Representative Overlapping Points.

A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines

A Python module for parallel optimization of expensive black-box functions

Official project repository for 'Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination'

This is a package for LiDARTag, described in paper: LiDARTag: A Real-Time Fiducial Tag System for Point Clouds

A general-purpose encoder-decoder framework for Tensorflow

PyTorch implementation of the ACL, 2021 paper Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks.

Torchlight2 lan game server tool - A message forwarding tool for Torchlight 2 lan game

To SMOTE, or not to SMOTE?