-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Improve hourglass performances #28
Comments
Strategy 1: Improve the loss functionProblemSince the addition of new images (representing different field of view of the spine) performances of the hourglass have dropped significantly (mainly due to the addition of new classes ~25 discs) leading to an increasing number of false positive detections. This problem was partially solved here but still numerous false positive detection are still occurring. IdeaSplit the loss function into two main components:
|
Strategy 2: Use random crop with larger fields of viewIdeaTo improve the performances and help the model to generalize, a new data augmentation function ResultsThe task still is too difficult for the model, the number of different classes is maybe to important. |
Strategy 3: Train 2 different modelsIdeaFinding and identifying all the 25 discs classes seems to be to difficult for one model, therefore, I will try to train 2 models:
These models will be train with and without the random cropping to evaluate their ability to generalize. Results... |
Strategy 4: Fixed window size with BCE lossIdea
Retry with the 25 classes but this time with a fixed size sliding window. The use of the Binary Cross Entropy will also be investigated to avoid having multiple classes for the same disc. Results... |
Description
This issue is meant to discuss about strategies to improve the performances of the hourglass network.
The text was updated successfully, but these errors were encountered: