A small fix to followup on
#5338
to ensure  ds_loss returns a constant, not an array

### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [ ] Breaking change (fix or new feature that would cause existing
functionality to change).
- [ ] New tests added to cover the changes.
- [x] Integration tests passed locally by running `./runtests.sh -f -u
--net --coverage`.
- [x] Quick tests passed locally by running `./runtests.sh --quick
--unittests --disttests`.
- [ ] In-line docstrings updated.
- [ ] Documentation updated, tested `make html` command in the `docs/`
folder.

Signed-off-by: myron <[email protected]>

This adds a DeepSupervisionLoss wrapper class around the main loss
function to accept a list of tensors returned from a deeply supervised
networks. The final loss is computed as the sum of weighted losses for
each of deep supervision levels (accounting for potential differences in
shapes between targets and ds outputs)

The wrapper class is designed to work with arbitrary existing loss,e.g.
```
    loss = DiceCELoss(to_onehot_y=True, softmax=True) 
    ds_loss = DeepSupervisionLoss(loss)
```

Whereas the existing loss accepts the input as a single Tensor, ds_loss
accepts the input as a list of Tensors (for each output of a deeply
supervised network). If only a simple Tensor input is provided, ds_loss
behaves exactly the same as the underlying loss.

I added unit tests too.



### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [ ] Breaking change (fix or new feature that would cause existing
functionality to change).
- [ ] New tests added to cover the changes.
- [ ] Integration tests passed locally by running `./runtests.sh -f -u
--net --coverage`.
- [ ] Quick tests passed locally by running `./runtests.sh --quick
--unittests --disttests`.
- [ ] In-line docstrings updated.
- [ ] Documentation updated, tested `make html` command in the `docs/`
folder.

Signed-off-by: myron <[email protected]>

A small fix to followup on
#5338
to ensure  ds_loss returns a constant, not an array

### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [ ] Breaking change (fix or new feature that would cause existing
functionality to change).
- [ ] New tests added to cover the changes.
- [x] Integration tests passed locally by running `./runtests.sh -f -u
--net --coverage`.
- [x] Quick tests passed locally by running `./runtests.sh --quick
--unittests --disttests`.
- [ ] In-line docstrings updated.
- [ ] Documentation updated, tested `make html` command in the `docs/`
folder.

Signed-off-by: myron <[email protected]>

This adds a DeepSupervisionLoss wrapper class around the main loss
function to accept a list of tensors returned from a deeply supervised
networks. The final loss is computed as the sum of weighted losses for
each of deep supervision levels (accounting for potential differences in
shapes between targets and ds outputs)

The wrapper class is designed to work with arbitrary existing loss,e.g.
```
    loss = DiceCELoss(to_onehot_y=True, softmax=True) 
    ds_loss = DeepSupervisionLoss(loss)
```

Whereas the existing loss accepts the input as a single Tensor, ds_loss
accepts the input as a list of Tensors (for each output of a deeply
supervised network). If only a simple Tensor input is provided, ds_loss
behaves exactly the same as the underlying loss.

I added unit tests too.



### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [ ] Breaking change (fix or new feature that would cause existing
functionality to change).
- [ ] New tests added to cover the changes.
- [ ] Integration tests passed locally by running `./runtests.sh -f -u
--net --coverage`.
- [ ] Quick tests passed locally by running `./runtests.sh --quick
--unittests --disttests`.
- [ ] In-line docstrings updated.
- [ ] Documentation updated, tested `make html` command in the `docs/`
folder.

Signed-off-by: myron <[email protected]>

A small fix to followup on
#5338
to ensure  ds_loss returns a constant, not an array

### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [ ] Breaking change (fix or new feature that would cause existing
functionality to change).
- [ ] New tests added to cover the changes.
- [x] Integration tests passed locally by running `./runtests.sh -f -u
--net --coverage`.
- [x] Quick tests passed locally by running `./runtests.sh --quick
--unittests --disttests`.
- [ ] In-line docstrings updated.
- [ ] Documentation updated, tested `make html` command in the `docs/`
folder.

Signed-off-by: myron <[email protected]>

This adds a DeepSupervisionLoss wrapper class around the main loss
function to accept a list of tensors returned from a deeply supervised
networks. The final loss is computed as the sum of weighted losses for
each of deep supervision levels (accounting for potential differences in
shapes between targets and ds outputs)

The wrapper class is designed to work with arbitrary existing loss,e.g.
```
    loss = DiceCELoss(to_onehot_y=True, softmax=True) 
    ds_loss = DeepSupervisionLoss(loss)
```

Whereas the existing loss accepts the input as a single Tensor, ds_loss
accepts the input as a list of Tensors (for each output of a deeply
supervised network). If only a simple Tensor input is provided, ds_loss
behaves exactly the same as the underlying loss.

I added unit tests too.



### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [ ] Breaking change (fix or new feature that would cause existing
functionality to change).
- [ ] New tests added to cover the changes.
- [ ] Integration tests passed locally by running `./runtests.sh -f -u
--net --coverage`.
- [ ] Quick tests passed locally by running `./runtests.sh --quick
--unittests --disttests`.
- [ ] In-line docstrings updated.
- [ ] Documentation updated, tested `make html` command in the `docs/`
folder.

Signed-off-by: myron <[email protected]>
Signed-off-by: KumoLiu <[email protected]>

A small fix to followup on
#5338
to ensure  ds_loss returns a constant, not an array

### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [ ] Breaking change (fix or new feature that would cause existing
functionality to change).
- [ ] New tests added to cover the changes.
- [x] Integration tests passed locally by running `./runtests.sh -f -u
--net --coverage`.
- [x] Quick tests passed locally by running `./runtests.sh --quick
--unittests --disttests`.
- [ ] In-line docstrings updated.
- [ ] Documentation updated, tested `make html` command in the `docs/`
folder.

Signed-off-by: myron <[email protected]>
Signed-off-by: KumoLiu <[email protected]>