Comments (2)
Hi @JayZhu0104 ,
Could you please provide additional details? The first step in debugging could be to separate the pre-training and fine-tuning steps. E.g., 1. whether fine-tuning from the released pre-training work? 2. what is the training from scratch baseline on your side (the 44.50 in the table)?
The smaller batch size could influence the performance. You could check its influence by comparing the training from scratch baseline (44.50) in the table.
Feel free to send me an email if I wasn't checking the git repo that frequently :)
Best,
Zhengyuan
from tap.
@JayZhu0104 May I know how many GPUs you're using for training and the corresponding training time? Thanks!
from tap.
Related Issues (20)
- Text Caption HOT 1
- TextCaps json file missing for TextVQA HOT 2
- Issue
- No targets for training HOT 1
- Different --model for using `textvqa_tap_ocrcc_best.ckpt`? HOT 1
- Reproduce of checkpoints HOT 1
- VQA output HOT 1
- Microsoft OCR data could not be found HOT 2
- Error during finetuning base model HOT 2
- Error of Pretraining User Defined Dataset HOT 5
- Validation Accuracy different from paper
- Hang when calculate validation accuracy
- A KEYERROR need to be solved--Emergency!
- Where is the text images in CC-OCR? HOT 4
- how to convert multi distributed GPU to single GPU
- TAP Pretraining on TextCaps, TextVQA, ST-VQA on TextVQA down-stream dataset
- Error in running pretrain because of torch.distributed
- Error when download the code HOT 2
- What is the val set of pre-train 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 tap.