Partial answer: Quoting a paper
"The advantage of such deep supervision is evident: (1)for small training data and relatively shallower networks, deep supervision functions as a strong “regularization” for classiﬁcation accuracy and learned features; (2) for large training data and deeper networks deep supervision makes it convenient to exploit the ...
Which CNN should I use for instance counting given that my dataset consists of labeled polygons?
CNNs for instance segmentation. To start with you can try Mask-RCNN. Here are all state of the art CNNs for instance segmentation. You will also find code for most of them.
I agree the metrics between your test set and validation set are quite close, but looking at your code it seems you may have run for the full 100 epochs.
keras supports early stopping, i.e. when scores fail to improve meaningfully you can have the model revert to the best scores it has seen to date:
You should ...
The loss is mostly a measure that helps the model learn and is not looked at too much when deciding which model to select. A more business oriented measure is often used for this, e.g. accuracy. Since in this case you are mostly interested in the dice score it would make most sense to select the model from epoch 8.
Three separate models (one per channel) will easily learn to predict the >channel category, but it will never output r0g1b2 and r2g3b0 classes in 64 class model because it have never seen these classes. How to overcome this problem?
The only way to solve this problem is to use channels (one for each skin damage type) for each pixel, and treat it as a ...
Diffgram is really great for this! I used it for a construction monitoring project. It's Open Source. From their site:
Semantic Segmentation Tools:
Auto Bordering: Automatically detects edges to create 100% coverage
masks. Simple select the intersecting shape.
Combo Shapes: Create shapes that are partially curves and partially straight lines.
Points to Full ...
There are a few models that are trained to analyse a sentence and classify each token (or recognise dependencies between words).
Part of speech tagging (POS) models assign to each word its function (noun, verb, ...) - have a look at this link
Dependency parsing (DP) models will recognize which words go together (in this case Angela and Merkel for instance) ...
So the question asks about why different loss function lead to different error scores.
So globally error is there to help us measure the level of discrimination between the output of the model and the actual output which we want to get.
Different loss functions have different formulations of this and are thus depending on the task itself, more appropriate to ...