# FOTS.PyTorch

**Repository Path**: wxs1129/FOTS.PyTorch

## Basic Information

- **Project Name**: FOTS.PyTorch
- **Description**: FOTS Pytorch Implementation
- **Primary Language**: C++
- **License**: BSD-3-Clause
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2019-09-29
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

## I have finished the detection branch and am still training the model to verify its correctness. All the features will be published to develop branch, and keep master stable. 
 - ICDAR Dataset 
 - SynthText 800K Dataset
 - detection branch 
 - eval
 - multi-gpu training
 
 
## Questions

- Should I fix weights of the backbone network, resnet50 ?
  ```python
  for param in self.backbone.parameters():
      param.requires_grad = False
  ```
 
 

# Introduction

This is a PyTorch implementation of [FOTS](https://arxiv.org/abs/1801.01671).