Comments (10)
@tson1997 hey, you should change the annotations of ICDAR2015 into COCO format(txt->json), and register your datasets. For more details that how to train your own custom datasets, please refer to https://github.com/facebookresearch/detectron2.
from textfusenet.
Hello @tson1997. If you were able to train your model on ICDAR 2015 dataset, can you provide any code snippets that you used for converting data and for registering?
from textfusenet.
@animesh-007 Hello, did you train successfully? I also encountered this problem and I want to know how to get train.json and test.json for ICDAR2015.
from textfusenet.
@animesh-007 Hello, did you train successfully? I also encountered this problem, and I want to know how to get train.json and test.json for ICDAR2015.
Yes, I was able to train the network successfully. You have to create train.json and test.json by yourself. As authors have not provided it yet as far, I remember.
from textfusenet.
@animesh-007 Hello, did you train successfully? I also encountered this problem, and I want to know how to get train.json and test.json for ICDAR2015.
Yes, I was able to train the network successfully. You have to create train.json and test.json by yourself. As authors have not provided it yet as far, I remember.
Thanks for the reply. I tried to create the json file by myself, but it seems that something get wrong. If possible, could you please provide the code used for converting? Thanks a lot.
from textfusenet.
@animesh-007 Thank you! I have send an email to [email protected] yesterday but I didn't got a response. I'm not sure whether you received the email.
from textfusenet.
Hi @chenf99 Can I also have your converting code as well?? My e-mail is jyjang1090@gmail. Thanks in advance!
from textfusenet.
@chenf99 Hi, can you kindly share the converting code? My e-mail is [email protected].
from textfusenet.
@chenf99 Can you please share the code for creating train/val.json file (data registration). My email is [email protected]
from textfusenet.
@chenf99 Hi, thanks for your hard-working, can you please share the code or the json file? My email is [email protected]
from textfusenet.
Related Issues (20)
- Some model parameters are not in the checkpoint? HOT 4
- Batch inference HOT 1
- Evaluating results HOT 1
- About the env installation HOT 1
- Average Precision
- 'keyError: non-existent config key: TEXTFUSENET_MUTIL_PATH_FUSE_ON' HOT 1
- NO_PUBKEY when running docker compose
- Train on Total-Text-Dataset
- TypeError when running demo
- Does the detection branch fuse global features?
- Not able to run test
- fail to reproduce ICDAR2015 result
- Installation error both with Dockerfile and conda environment HOT 2
- Hello, How to convert the PTH model into an ONNX format model HOT 1
- What is the parameter quantity of the model?
- docker HOT 1
- Error in installation HOT 3
- Is it possible to run demo on torch>=1.6.0? HOT 1
- corrupted pre-trained models
- 关于生成字符伪标签mask的问题 HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from textfusenet.