Comments (5)
Hi,
I think that the cost is not supposed to become negative, not sure why this happens.
It could be that this points to a problem, or maybe it's just some unimportant thing like a wrong scale of the loss values.
Considering that the accuracy still increases, it might be that it will just work fine. It would be good if you can try to make a recognition with this model, and see if it works as usual.
from returnn.
What loss is that? Depending on the loss, it sure can become negative. For example, I think the CTC loss can become negative.
from returnn.
Its CTC loss that I am using. I have not made any changes to the loss function (using the same as given with returnn library). I will update the final results once the training stops...So far accuracy improving continuously(surprising!) and loss going more negative.
from returnn.
The CTC loss (Eq. 12 in ftp://ftp.idsia.ch/pub/juergen/icml2006.pdf ) cannot become negative: each summand is ln(p), where 0 <= p <= 1 which means that -infty <= ln(p) <= 0 which means the negative sum cannot become negative in theory. Don't know why it's happening here anyway, could be a bug. First let's see if you get good results anyway.
from returnn.
Hello, Thanks for the reply. I figures out that there was one character with single instance in the dataset. I guess, this was causing trouble. Once I remove that line image and took the revised character set, it is giving the desired behavior. I didnt expect the super-high imbalance in classes can result in such a disaster :(
Thanks!
from returnn.
Related Issues (20)
- Support `torch.compile` for RF
- RF backend: PyTorch code
- Different effective learning rate reported over gpus HOT 11
- CUDA error: initialization error HOT 3
- MultiProcDataset inside PyTorch DataLoader with num_workers>0, multiple issues HOT 4
- RuntimeError: CUDA error: unspecified launch failure HOT 2
- NonDaemonicSpawnProcess hangs at exit HOT 2
- High memory usage with datasets (specifically when multi procs are used)
- Hang at exit in TDL worker in multiprocessing `_run_finalizers`, deadlock in `_wait_for_tstate_lock`? HOT 6
- Hang HOT 2
- Returnn Native after using different apptainer uses old compilation HOT 6
- MetaDataset with sequence list filter file
- HDFDataset (or generic dataset) post processing HOT 15
- Dataset batching like ESPnet support
- torch.nn.functional.conv2d: RuntimeError: GET was unable to find an engine to execute this computation HOT 1
- TensorFlow 2.14 degradation in WER HOT 2
- Updates for recent TensorFlow version
- Hang in dataset iterator HOT 5
- Log GPU device for torch backend HOT 2
- torch.onnx.export requires input_names and output_names to be in order HOT 12
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 returnn.