Comments (6)
请参考文章关于更新MW-Net参数的数学表达式。
from meta-weight-net.
optimizer_c中优化的是vnet的参数,但是损失l_g_meta中我没有看到vnet网络的参与,我有点想不清楚网络是如何迭代的
损失l_g_meta是meta_model和vnet网络的共同参与计算的,所以是在一个计算图中的。这也是meta_model存在的意义,做一个桥梁作用。
226行:
l_g_meta.backward()
这一步更新的不仅是临时模型的参数,也包含了vnet
from meta-weight-net.
@xjtushujun @jingzhengli 您好,我也是看到这个地方,有些不理解。meta_model 本身是不包含vnet的,vnet的梯度是怎么计算出来的呢?我发现meta_model.update_params这行代码应该很重要,我去掉这行,vnet的梯度就不能计算了。可是这行代码调用的函数 只和meta_model相关,是怎么能和vnet有联系的呢?如果方便 麻烦讲解一下,谢谢您!
from meta-weight-net.
It's related to the update_params() method defined in MetaModule class in resnet.py.
from meta-weight-net.
关于网络参数更新的问题想请教一下,
optimizer_c.zero_grad()
l_g_meta.backward()
optimizer_c.step()
这几行应该是要更新vnet网络的参数,但是vnet.state_dict()观察发现网络参数并没有变化。还有后边优化model参数的时候也是一样的问题,麻烦解释一下,谢谢!
from meta-weight-net.
same problem, can anyone explain this? I understand all the math in the paper, but I dont understand the code for gradient calculation.
from meta-weight-net.
Related Issues (15)
- The accuracy of BaseModel is 88.5 when the noise rate is 0.4? HOT 4
- 有关GPU的问题 HOT 1
- 关于baseline精度问题 HOT 3
- 请问本文的方法和L2RW的比较 HOT 1
- 请问一下能否用Adam作为optimizer_model的优化算法? HOT 1
- tabular data/ noisy instances
- 数据集划分
- how to draw the accuracy curve
- Can you provide the code for imbalanced dataloader? HOT 2
- 关于模型的问题 HOT 1
- About the effectiveness HOT 2
- About the details of learning rate HOT 1
- 计算图问题 HOT 2
- 想问问大佬那个Figure 1(f)的权重跟Loss的分布图是怎么画的。
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-weight-net.