Comments (5)
If the number of pictures in the second increment is much smaller than that in the first increment, how should I set these two parameters
from pycil.
When fixed memory is set to false, memory size is used, which means that we keep memory size images for all the old classes, which means that for each of the k old categories, we keep memory size/k(floor) images.
On the contrary, when fixed memory is set to true, memory_per_class will be used, which means that we will keep memory_per_class images for each category. In other words, its memory size increases with the number of categories.
from pycil.
In most cases, to be fair, when training cifar100 and imagenet100, we set memory size to 2000, and when training imagenet1000, we set memory size to 20000.
from pycil.
When fixed memory is set to false, memory size is used, which means that we keep memory size images for all the old classes, which means that for each of the k old categories, we keep memory size/k(floor) images.
On the contrary, when fixed memory is set to true, memory_per_class will be used, which means that we will keep memory_per_class images for each category. In other words, its memory size increases with the number of categories.
I probably understand. Thank you for your explanation
from pycil.
Thanks for your interests. 😊
from pycil.
Related Issues (20)
- Could you add our model to your responsity? HOT 2
- Why is there no downsampling in the first convolution layer of resnet for imagenet dataset? HOT 4
- Cannot run pre-trained ResNet18. RuntimeError: Error(s) in loading state_dict for ResNet: Missing key(s) in state_dict HOT 2
- some question about BEEF
- Code to plot? HOT 1
- 当我运行fetril方法,使用ImageNet数据集,data_manager.py报错 HOT 5
- TypeError: pic should be PIL Image or ndarray. Got <class 'torch.Tensor'> HOT 2
- GEM issue
- about memory size and train HOT 1
- some weight problem HOT 8
- Adding reproduced results to README HOT 1
- Is there any problem with the current code running by default settings? HOT 2
- Resnet why "init_cls"=="increment"? HOT 2
- PyCil's Resnet different from Default implementation? Why? HOT 2
- low accuracy on ewc HOT 1
- about model ,about cifa10 HOT 2
- About DER HOT 5
- pretrained model HOT 1
- bug in eval_task() HOT 2
- about class 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 pycil.