def get_preds(learn: Learner,
dl: DataLoader,
with_loss: bool = False,
n_batch: Optional[int] = None,
pbar: Optional[PBar] = None) -> List[Tensor]:
"""Return predictions and targets on `dl` dataset.
This function is the same as fastai's Learner.get_preds except this allows an external DataLoader.
For more details about Learner.get_preds, see:
https://github.com/fastai/fastai/blob/master/fastai/basic_train.py
Args:
learn: Learner object that will be used for prediction
dl: DataLoader the model will use to load samples
with_loss: If True, it will also return the loss on each prediction
n_batch: Number of batches to predict. If not specified, it will run the predictions for n batches
where n = sample size // BATCH_SIZE
pbar: ProgressBar object
"""
lf = learn.loss_func if with_loss else None
return fastai.basic_train.get_preds(
learn.model,
dl,
cb_handler=CallbackHandler(learn.callbacks),
activ=_loss_func2activ(learn.loss_func),
loss_func=lf,
n_batch=n_batch,
pbar=pbar)
def get_preds(learn: Learner,
dl: DataLoader,
with_loss: bool = False,
n_batch: Optional[int] = None,
pbar: Optional[PBar] = None) -> List[Tensor]:
"""Return predictions and targets on `dl` dataset.
This function is the same as fastai's Learner.get_preds except this allows an external DataLoader.
For more details about Learner.get_preds, see:
https://github.com/fastai/fastai/blob/master/fastai/basic_train.py
Args:
learn: Learner object that will be used for prediction
dl: DataLoader the model will use to load samples
with_loss: If True, it will also return the loss on each prediction
n_batch: Number of batches to predict. If not specified, it will run the predictions for n batches
where n = sample size // BATCH_SIZE
pbar: ProgressBar object
"""
# Note: In Fastai, for DatasetType.Train, only the output of complete minibatches is computed. Ie if one has 101 images,
# and uses a minibatch size of 16, then len(feats) is 96 and not 101. For DatasetType.Valid this is not the case,
# and len(feats) is as expected 101. A way around this is to use DatasetType.Fix instead when referring to the training set.
# See e.g. issue: https://forums.fast.ai/t/get-preds-returning-less-results-than-length-of-original-dataset/34148
if dl == DatasetType.Train:
dl = DatasetType.Fix
lf = learn.loss_func if with_loss else None
return fastai.basic_train.get_preds(
learn.model,
dl,
cb_handler=CallbackHandler(learn.callbacks),
activ=_loss_func2activ(learn.loss_func),
loss_func=lf,
n_batch=n_batch,
pbar=pbar)
def _tta_only(learn:Learner, ds_type:DatasetType=DatasetType.Valid) -> Iterator[List[Tensor]]:
"Computes the outputs for several augmented inputs for TTA"
dl = learn.dl(ds_type)
ds = dl.dataset
old = ds.tfms
augm_tfm = [o for o in learn.data.train_ds.tfms]
try:
pbar = master_bar(range(8))
for i in pbar:
ds.tfms = augm_tfm
yield get_preds(learn.model, dl, pbar=pbar, activ=_loss_func2activ(learn.loss_func))[0]
finally: ds.tfms = old
def custom_tta(learn:Learner, ds_type:DatasetType=DatasetType.Valid):
dl = learn.dl(ds_type)
ds = dl.dataset
old_open_image = fastai.vision.data.open_image
try:
maxNumberOfCrops = 20
for i in range(maxNumberOfCrops):
#print("starting")
setupNewCrop(i)
yield get_preds(learn.model, dl, activ=_loss_func2activ(learn.loss_func))[0]
finally:
fastai.vision.data.open_image = old_open_image
def _seg_tta_only_v1(
learn: Learner,
ds_type: DatasetType = DatasetType.Valid) -> Iterator[List[Tensor]]:
"Computes the outputs for non-flip and flip_lr augmented inputs"
dl = learn.dl(ds_type)
ds = dl.dataset
old = ds.tfms
try:
pbar = master_bar(range(2))
for i in pbar:
tfm = [] # to remove random crop resize aug
if i: tfm.append(flip_lr(p=1.))
ds.tfms = tfm
yield get_preds(learn.model,
dl,
pbar=pbar,
activ=_loss_func2activ(learn.loss_func))[0]
finally:
ds.tfms = old