Comments (9)
@alexliyang Please wait for our arxiv manuscript, which will provide a detailed definition of the loss function.
from tencent-ml-images.
thx a lot
Now I want to train a classical model, samples do not use bbox , only classic labels, how to use your loss function?
Thanks
from tencent-ml-images.
@alexliyang In the provided code, we also didn't use bbox. So you can directly copy the code of the loss function. Our Arxiv manuscript is expected to be released in one week.
from tencent-ml-images.
OK, thanks, I will use this loss to train my model.
and another question: my class_num is 10, whether I should add 1 to class_num i.e. class_num = 11 when I train the model or not ? and in fact i only have 10 classes sample data.
Thanks
from tencent-ml-images.
@alexliyang You mean adding a rejection class? We have not tried that. The main difficulty may be how to obtain the training sample for the rejection class. If you train with 10 classes, if the posteriors of all classes are lower than a threshold, it can be considered as rejection.
from tencent-ml-images.
@wubaoyuan thanks, although I do not understand your loss function , now I copy it and use it to train my model, I find that ,the every step loss value and mean loss value are smaller than the value from softmax_cross_entropy_with_logits function, but the test acc is not better than using softmax_cross_entropy_with_logits function.
Maybe I used it not correctly
from tencent-ml-images.
@wubaoyuan Have you Arxiv manuscript been released?
from tencent-ml-images.
@Jason-xin Already finished, in proof-reading. Maybe one week.
from tencent-ml-images.
you can see the function: torch.nn.BCEWithLogitsLoss()
from tencent-ml-images.
Related Issues (20)
- Who could tell me the size of the whole dataset? HOT 4
- Could you please explain why is used 'imgs = imgs[...,::-1]' in extract_feature.py HOT 1
- 训练的时候train_accuracy一直下降 HOT 2
- 请问哪个脚本是用于训练多标签分类的?
- 不管是train还是finetune,咋都不把跑验证集的加上去。 HOT 2
- a question about the num_class
- How to download openimage by other ways?
- non_neg_mask not work
- checkpoint ckpt-resnet101-mlimages 图片分类报错 HOT 7
- Where to get imagenet urls?
- Cropping's affect on annatations? HOT 1
- Annotations? HOT 1
- Number of categories in openimages? HOT 1
- 特征提取对应关系
- over-fitting
- wrong label hierarchy
- 请问能够提供ImageNet Whole Dataset的国内数据镜像地址吗? HOT 3
- What is the size of the whole dataset?
- 关于ImageNet数据集获取
- 训练的过程中报错image_size must contain 3 elements[4]
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 tencent-ml-images.