Comments (4)
Hey Haelles,
If you look at src/cct:231 you'll see that we hard code CCT (and CVT) to have a dropout of 0. Though ViTLite line 161 has a dropout of 0.1.
The lines that you are looking at (src/transformers.py:62) are called by all the models. They all use the same Transformer Encoder structure. But CCT and CVT will not apply dropout and you can safely ignore that for those models, unless you want to do some hyper parameter testing yourself.
I can see the ambiguity in how we wrote it. We'll make sure this is more clear in the next version of the paper. Thank you!
from compact-transformers.
Hey Haelles,
If you look at src/cct:231 you'll see that we hard code CCT (and CVT) to have a dropout of 0. Though ViTLite line 161 has a dropout of 0.1.
The lines that you are looking at (src/transformers.py:62) are called by all the models. They all use the same Transformer Encoder structure. But CCT and CVT will not apply dropout and you can safely ignore that for those models, unless you want to do some hyper parameter testing yourself.
I can see the ambiguity in how we wrote it. We'll make sure this is more clear in the next version of the paper. Thank you!
Thank you for your reply.
If I may ask again, I added print(self.dropout1)
at src/transformers.py:62 and got Dropout(p=0.1, inplace=False)
. I think there is something wrong here src/cct.py:109, the value of parameter "dropout" should be "dropout" rather than "dropout_rate". The value of "dropout_rate" is 0.1 here.
I used python main.py --model cct_7 --conv-size 3 --conv-layers 1 path/to/cifar10
Really appreciate your help!
from compact-transformers.
Hello @Haelles
Thank you for bringing this to our attention. We noticed there was a small key mismatch in this version, and we just fixed it in the latest commit (39b45de).
from compact-transformers.
Thanks for your response!
from compact-transformers.
Related Issues (20)
- Config for training Flowers SOTA HOT 6
- Text Masked Attention: TextTokenizer.forward() should return "new_mask" HOT 2
- AttributeError: 'TransformerClassifier' object has no attribute 'num_tokens' HOT 7
- The question about Vit-lite model HOT 2
- Fine Tuning HOT 1
- validation set HOT 1
- Image scaling and normalization HOT 1
- Dino self-supervised vision transformer HOT 1
- Output of the CCT classifier HOT 2
- Question about the batch size HOT 2
- Thank you for your nice work | Question on Flowers dataset HOT 10
- Training and evaluation scripts in examples folder HOT 1
- NLP Results and CCT size HOT 2
- something wrong with vit-lite HOT 2
- About Mask Autoencoder HOT 2
- Information about Text Classifier HOT 7
- x += self.positional_emb mismatch HOT 2
- yml file settings
- How to test my trained model?
- Unable to Replicate Text Classification Results 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 compact-transformers.