Comments (4)
hikettei
commented on June 3, 2024
推定される原因：
LinearLayer: hidden-size -> vocab-size
Embedding
from cl-waffe.
hikettei
commented on June 3, 2024
cl-waffe initializes weights with Orthogonal/Xariver/He in response to their activation/model, but it won't work.
As I tried the same calculations on PyTorch (Seq2Seq with SimpleRNN), the value of loss is the same as cl-waffe, however optimizing is going well while cl-waffe is not.
from cl-waffe.
hikettei
commented on June 3, 2024
Hmm, i guess i need more tests, working on branch fix-rnn
from cl-waffe.
hikettei
commented on June 3, 2024
Fixed at #103, !softmax substracts x by the average of x but the axes was a different
from cl-waffe.
Related Issues (19)
- The backpropagation of !split is undefined. HOT 2
- Split large files into small HOT 1
- !argmax/!argmin requires tensor to be copied.
- To add: Dispatch nodes based on a given tensor’s backend
- The performance of call-forward and call-backward. HOT 4
- call-forward, call-backward is reducible HOT 4
- Support GPU
- (setf !aref) is ugly
- Add LSTM/GRU HOT 1
- Add Conv/Pooling
- Save and restore the weights of model HOT 1
- Add: DataTypeまわりの機能がもっと欲しい HOT 1
- Implement !expands
- Sampling beta distributions is failed with alpha=1.0, beta=1.0
- Add: (with-config ~) macro
- 重みの初期化手法について HOT 1
- TODO HOT 8
- Allowing other options to use matrices in cl-waffe 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 cl-waffe.