Comments (4)
I modified the num head, which was originally 2. Speaking of which, I'd have to say that your code is really poorly written.
I used a new dataset with more channels than seq_len, and you ended up swapping dimensions and it all went haywire.
Another point is that you use the torch.cuda package in the data augmentation and then provide an option to not use the GPU. hhh
I guess this is a very early version, right? Can you provide the final version?
from tfc-pretraining.
Can your model solve multivariate time series forecasting? If not, why do you provide the option of multiple channels?
from tfc-pretraining.
I think you can find it in the diff of 6ed4dae.
from tfc-pretraining.
Related Issues (20)
- DataTransform_FD funtion implement is inconsistent with the paper? HOT 1
- Code missing HOT 2
- KNN baseline not reproducible and incorrect information about the HAR dataset HOT 1
- Availability of pre-trained weights HOT 1
- Many-to-one experiments HOT 2
- bugs of DataTransform_TD HOT 1
- The problem with pre-training HOT 3
- the permutation augmentation method HOT 1
- Access to data transformation code
- backbone HOT 7
- some details questions HOT 4
- Time-Frequency Consistency Loss is not utilized HOT 10
- Accuracy metrics are generally not computed at the right time - attempted corrected code provided (trainer.py) HOT 2
- The MLP classification model output is not logit and vanilla cross entropy loss is used.
- The challenge of reproducing the baselines of CLOCS
- [BUG] Error preprocesing files
- "data_pre_processing" in simclr
- NO well-processed datasets and requirements.yml HOT 2
- Possible fatal errors in DataTransform function HOT 3
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 tfc-pretraining.