Comments (8)
I am trying with medical images but still figuring out the correct/best dimensions for the projection network. The loss is not converging if I use the default design and hyperparameters.
Did you try it with medical images?
from barlowtwins.
Yea I have the same issue here, no loss convergence. I think I'm also going to try playing around with transformations, feels like the default ones are too strong to permit learning of any sorts. Would you like to take this conversation off issues
to discuss a little more in detail? (email: [email protected])
from barlowtwins.
Dear Joseph,
I tried to send you an email, but your address didn't work. My address: [email protected]
Currently, I am trying to use ResNet50 equipped with e2conv (https://github.com/QUVA-Lab/e2cnn) in BarlowTwins model with additional CLD loss (https://github.com/frank-xwang/CLD-UnsupervisedLearning) . According to papers, e2cnn would be helpful to medical images that have rotation equivalent (e.g. histological images), and CLD could accelerate converging. I would like to use this model to cluster some gray-scale images. My images are not medical images, but they are also in grey-scale, rotation equivalent, and monotonous. I think my data may share some similarities with yours. I started to train my network today, and so far my loss are dropping, and I will let you know if my design could work out.
Have fun with your experiment!
from barlowtwins.
Promising application! Please keep us updated with your progress on this thread for everyone to benefit, and don't hesitate to ask if you have any question for us. Thanks!
from barlowtwins.
Hey Harold,
Sounds interesting, can't wait to hear back from your concerning your experiments. For the moment I have tried soft augmentations, using outputs from different convolution layers, playing around with the learning rate and using pyramidal avg-pooling instead of global average pooling at the final layer. Most of the experiments for the moment haven't lead to significant loss convergence, except maybe for pyramidal avg-pooling where the loss was erratic.
Hope this helps :)
from barlowtwins.
I had some bad news. After some experiments, I found that the loss would drop significantly for thousands of steps, but then got bigger and bigger. I am still playing around with the learning rate, but it can be tricky. I wonder if you have tried simsiam?
from barlowtwins.
is there anyone with some experience on this topic? currently the loss does not go down properly, it seems stuck at around 4000. tried to change the learning rate, but doesnt seem to help in any way.
from barlowtwins.
Anyone have success?
from barlowtwins.
Related Issues (20)
- Issue loading checkpoint.pth file HOT 1
- Augmentation Distribution HOT 1
- Will BarlowTwins overfit on the training data?
- When using the own dataset, loss is around 10,000 HOT 8
- About the last normalization layer HOT 1
- Dose we can add distorted image, like Y_a, Y_b, Y_c?
- A question on the BT loss with Batch Norm layers HOT 4
- Start index for each epoch HOT 3
- weight update for step=0,epoch=0 get's missed. HOT 2
- Applications on one-dimensional signal datasets HOT 4
- Where could we find the "reproduced version" of the other SSL methods HOT 1
- Question about Fig. 4 in the paper HOT 4
- Quality of Embeddings
- Possible bug on the loss computation HOT 1
- Error in saving resnet50.pth HOT 2
- efficiency proposal HOT 1
- NaN's introduced during training.
- providing the linear ImageNet classifier weights
- Pre-training model for CIFAR
- Why c.div_(self.args.batch_size) is needed? 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 barlowtwins.