Comments (8)
And I've changed the ResNet from 101 to 50, and multiscale training has only used 480 and 512
from meta-detr.
Thanks for your interest. Please check if you correctly follow our training scripts.
On Pascal VOC Split 1, one training epoch takes around 19-20 minutes based on my training logs.
from meta-detr.
Thanks for your interest. Please check if you correctly follow our training scripts.
On Pascal VOC Split 1, one training epoch takes around 19-20 minutes based on my training logs.
Thanks for your reply.
In your paper, I see you use 8 × v100, how many batchsize do you set? And I want to konw the time one epoch when training on MSCOCO.
I set batchsize=4, and use one 2080TI on MSCOCO to training, which takes one day.
from meta-detr.
I also meet this question, and I use one Tesla V100 GPU(32G), and I change batch_size from 4 to 8, it seems like need 11 hours to train one epoch.
from meta-detr.
Thanks for your interest. Please check if you correctly follow our training scripts.
On Pascal VOC Split 1, one training epoch takes around 19-20 minutes based on my training logs.Thanks for your reply. In your paper, I see you use 8 × v100, how many batchsize do you set? And I want to konw the time one epoch when training on MSCOCO. I set batchsize=4, and use one 2080TI on MSCOCO to training, which takes one day.
Is it all very slow during training? The 3060Ti I use is too slow. Can I add your contact information so we can discuss related issues.
from meta-detr.
from meta-detr.
Thanks for your interest. Please check if you correctly follow our training scripts.
On Pascal VOC Split 1, one training epoch takes around 19-20 minutes based on my training logs.Thanks for your reply. In your paper, I see you use 8 × v100, how many batchsize do you set? And I want to konw the time one epoch when training on MSCOCO. I set batchsize=4, and use one 2080TI on MSCOCO to training, which takes one day.
Hello, may I ask if your problem has been solved? At present, I am also using 2070, and batch_size=4, the speed is also very slow, I hope to get your help, thank you
from meta-detr.
from meta-detr.
Related Issues (20)
- Regarding Background Encoding and Prototype HOT 2
- coco fine-tuning parameters
- Can you provide the t-SNE visualization code about mmdet? HOT 3
- Is the results of multi-scale version better and why not use it? HOT 1
- Some questions about t-SNE HOT 1
- There was a problem trying to train the code.
- How to evaluate the base training performance?
- split few-shot
- could you improve the training efficiency?
- Could you provide the fine-tuned weights? HOT 1
- About visualize the results.
- How long does it take Meta-Finetuning to converge?
- Performance of Meta-DETR without meta-finetuning? HOT 7
- Some questions about QSAttn. HOT 8
- 训练自己的数据集 HOT 1
- 在训练自己的数据集时,类别数报错。 HOT 2
- Questions about Task Encodings, Class Prototypes, and Category Codes
- How to generate my own few_shot file just as "coco_fewshot" when finetune on custom dataset? HOT 1
- 您好,请问可以公开一下论文中可视化结果的相关代码吗? HOT 1
- Fine-tuning time HOT 1
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 meta-detr.