def __init__(self,
image_features_h5path: str,
in_memory: bool = True) -> None:
self._image_features_reader = ImageFeaturesReader(
image_features_h5path, in_memory)
self._image_ids = sorted(list(self._image_features_reader._map.keys()))
def __init__(
self,
vocabulary: Vocabulary,
captions_jsonpath: str,
image_features_h5path: str,
max_caption_length: int = 20,
in_memory: bool = True,
) -> None:
self._vocabulary = vocabulary
self._image_features_reader = ImageFeaturesReader(image_features_h5path, in_memory)
self._captions_reader = CocoCaptionsReader(captions_jsonpath)
self._max_caption_length = max_caption_length
def __init__(self, vocabulary,
captions_jsonpath,
image_features_h5path,
classes_per_it,
num_samples,
iterations,
max_caption_length=20,
in_memory=False):
'''
Initialize the PrototypicalBatchSampler object
Args:
- labels: an iterable containing all the labels for the current dataset
samples indexes will be infered from this iterable.
- classes_per_it: number of random classes for each iteration
- num_samples: number of samples for each iteration for each class (support + query)
- iterations: number of iterations (episodes) per epoch
'''
super(PrototypicalBatchSampler, self).__init__()
self.vocabulary = vocabulary
self._image_features_reader = ImageFeaturesReader(image_features_h5path, in_memory)
self._captions_reader = CocoCaptionsReader(captions_jsonpath)
self._max_caption_length = max_caption_length
self.classes_per_it = classes_per_it
self.sample_per_class = num_samples
self.iterations = iterations
self.classes, self.counts = np.unique(self.labels, return_counts=True)
self.classes = torch.LongTensor(self.classes)
# create a matrix, indexes, of dim: classes X max(elements per class)
# fill it with nans
# for every class c, fill the relative row with the indices samples belonging to c
# in numel_per_class we store the number of samples for each class/row
self.idxs = range(len(self.labels))
self.indexes = np.empty((len(self.classes), max(self.counts)), dtype=int) * np.nan
self.indexes = torch.Tensor(self.indexes)
self.numel_per_class = torch.zeros_like(self.classes)
for idx, label in enumerate(self.labels):
label_idx = np.argwhere(self.classes == label).item()
self.indexes[label_idx, np.where(np.isnan(self.indexes[label_idx]))[0][0]] = idx
self.numel_per_class[label_idx] += 1