Comments (3)
I managed to create a json file which works. Here is the example I come up with:
{
"d_model": 160,
"h": 8,
"attn_type": "entmax15",
"d_ff": 16,
"dropout": 0.3,
"num_class": 2000,
"embedding_dim": 20,
"cov_dim": 16,
"N": 3,
"predict_steps": 24,
"train_window": 192,
"batch_size": 64,
"predict_batch": 64,
"num_epochs": 500,
"lr_d": 0.0001,
"lr": 6.25e-5,
"lr_schedule": "warmup_cosine",
"lr_warmup": 0.002,
"predict_start": 168,
"gan": true,
"test_predict_start": 168
}
it must be added under: experiments\test\parameters.json. Most of the attributes are self explanatory, except for num_class, which I couldn't figure it out yet. If you're noticing any difference from the paper please let me know, so I can modify the example.
from ast.
+1
from ast.
I managed to create a json file which works. Here is the example I come up with:
{
"d_model": 160,
"h": 8,
"attn_type": "entmax15",
"d_ff": 16,
"dropout": 0.3,
"num_class": 2000,
"embedding_dim": 20,
"cov_dim": 16,
"N": 3,
"predict_steps": 24,
"train_window": 192,
"batch_size": 64,
"predict_batch": 64,
"num_epochs": 500,
"lr_d": 0.0001,
"lr": 6.25e-5,
"lr_schedule": "warmup_cosine",
"lr_warmup": 0.002,
"predict_start": 168,
"gan": true,
"test_predict_start": 168
}it must be added under: experiments\test\parameters.json. Most of the attributes are self explanatory, except for num_class, which I couldn't figure it out yet. If you're noticing any difference from the paper please let me know, so I can modify the example.
@razvanc92 thanks for share the json,I tried to run the training process, but I am stuck in many Ipython sections
from ast.
Related Issues (10)
- code HOT 4
- RuntimeError: The size of tensor a (160) must match the size of tensor b (24) at non-singleton dimension 2 HOT 1
- The data set HOT 1
- preprocess_data.py reference
- Code to reproduce experiments
- requirement.txt
- how does the embed() work in gan_transformer.py? HOT 3
- How to update the q90? HOT 1
- There seems to be something wrong with function test() in gan_transformer.py ? 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 ast.