Comments (1)
Hi,
Thanks for pointing that out. The four lines you mentioned are the old version of frequency augmentation, they should be commented out. The augmentations are implemented by the following:
def DataTransform_FD(sample, config):
aug_1 = remove_frequency(sample, pertub_ratio=0.1)
aug_2 = add_frequency(sample, pertub_ratio=0.1)
aug_F = aug_1 + aug_2
return aug_F
def remove_frequency(x, pertub_ratio=0.0):
mask = torch.FloatTensor(x.shape).uniform_() > pertub_ratio # maskout_ratio are False
mask = mask.to(x.device)
return x*mask
def add_frequency(x, pertub_ratio=0.0):
mask = torch.FloatTensor(x.shape).uniform_() > (1-pertub_ratio) # only pertub_ratio of all values are True
mask = mask.to(x.device)
Moreover, we have updated the TFC implementation. Please check more details in the Updates on Jan 2023 section of the repo readme. In summary:
- Fixed bugs, cleaned the codes, and added comments for better understanding.
- For the contrastive encoders (in both time and frequency domains), we replaced the 3 layers of CNN blocks with 2 layers of Transformer.
- For the downstream classifier, we added a KNN classifier in parallel with the original MLP (2-layer) classifier.
- Shared more ideas that may improve the TF-C framework in follow-up works.
from tfc-pretraining.
Related Issues (20)
- 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
- Where is 3-layer 1 D Resnet? HOT 4
- 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
- the baseline method code like TNC, CPC, etc.
- It's difficult to replicate the results of the paper HOT 2
- Repetitive channels in the Gesture Dataset HOT 1
- baseline_requirements with conflicts
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.