def hard_negative_multilabel(self):
"""Hard Negative Sampling based on multilabel assumption
Search the negative sample with largest distance (smallest sim)
with the anchor within self._k negative samplels
"""
# During early iterations of sampling, use random sampling instead
if self._iteration <= self._n:
return self.random_multilabel()
anchor_class_id, negative_class_id = np.random.choice(
self._index.keys(), 2)
anchor_id, positive_id = np.random.choice(
self._index[anchor_class_id], 2)
negative_ids = np.random.choice(
self._index[negative_class_id], self._k)
# calcualte the smallest simlarity one with negatives
anchor_label = parse_label(self._labels[anchor_id])
positive_label = parse_label(self._labels[positive_id])
negative_labels = [parse_label(self._labels[negative_id]) for
negative_id in negative_ids]
p_sim = intersect_sim(anchor_label, positive_label)
n_sims = np.array(
[intersect_sim(anchor_label, negative_label) for
negative_label in negative_labels])
min_sim_id = np.argmin(n_sims)
negative_id = negative_ids[min_sim_id]
n_sim = n_sims[min_sim_id]
margin = p_sim - n_sim
return (anchor_id, positive_id, negative_id, margin)
def hard_negative_multilabel(self):
"""Hard Negative Sampling based on multilabel assumption
Search the negative sample with largest distance (smallest sim)
with the anchor within self._k negative samplels
"""
# During early iterations of sampling, use random sampling instead
if self._iteration <= self._n:
return self.random_multilabel()
anchor_class_id, negative_class_id = np.random.choice(
self._index.keys(), 2)
anchor_id, positive_id = np.random.choice(self._index[anchor_class_id],
2)
negative_ids = np.random.choice(self._index[negative_class_id],
self._k)
# calcualte the smallest simlarity one with negatives
anchor_label = parse_label(self._labels[anchor_id])
positive_label = parse_label(self._labels[positive_id])
negative_labels = [
parse_label(self._labels[negative_id])
for negative_id in negative_ids
]
p_sim = intersect_sim(anchor_label, positive_label)
n_sims = np.array([
intersect_sim(anchor_label, negative_label)
for negative_label in negative_labels
])
min_sim_id = np.argmin(n_sims)
negative_id = negative_ids[min_sim_id]
n_sim = n_sims[min_sim_id]
margin = p_sim - n_sim
return (anchor_id, positive_id, negative_id, margin)
def random_multilabel(self):
"""Random Sampling under the assumption of multilabels
All are similar to random sampling
the difference is to involve a distance ofsimilarity measurements
in addition.
Or equvilent, as a margin of anchor sample
between positive and negative
"""
anchor_id, positive_id, negative_id = self.random_sampling()
# calculate the distance of similarity score / margin
anchor_label = parse_label(self._labels[anchor_id])
positive_label = parse_label(self._labels[positive_id])
negative_label = parse_label(self._labels[negative_id])
p_sim = intersect_sim(anchor_label, positive_label)
n_sim = intersect_sim(anchor_label, negative_label)
margin = p_sim - n_sim
return (anchor_id, positive_id, negative_id, margin)
def random_multilabel(self):
"""Random Sampling under the assumption of multilabels
All are similar to random sampling
the difference is to involve a distance ofsimilarity measurements
in addition.
Or equvilent, as a margin of anchor sample
between positive and negative
"""
anchor_id, positive_id, negative_id = self.random_sampling()
# calculate the distance of similarity score / margin
anchor_label = parse_label(self._labels[anchor_id])
positive_label = parse_label(self._labels[positive_id])
negative_label = parse_label(self._labels[negative_id])
p_sim = intersect_sim(anchor_label, positive_label)
n_sim = intersect_sim(anchor_label, negative_label)
margin = p_sim - n_sim
return (anchor_id, positive_id, negative_id, margin)
def calculate_label_dim(self):
"""Calculate the dimension of labels
by calculating the lenth of label set
"""
all_labels = []
for label_str in self._label:
label = parse_label(label_str)
all_labels += label
all_labels = set(all_labels)
self._label_dim = len(all_labels)
def calculate_label_dim(self):
"""Calculate the dimension of labels
by calculating the lenth of label set
"""
all_labels = []
for label_str in self._label:
label = parse_label(label_str)
all_labels += label
all_labels = set(all_labels)
self._label_dim = len(all_labels)
def _build_index(self):
"""Build Index to randomly fetch samples from data
The index is in the format of python dict
{label: [list of sample id]}
"""
self._sample_count = len(self._labels)
self._index = dict()
for id in range(self._sample_count):
# parse label and insert into self._index
labels_ = parse_label(self._labels[id])
for label_ in labels_:
if label_ in self._index.keys():
self._index[label_].append(id)
else:
self._index[label_] = [id]
def get_a_datum(self):
if self._compressed:
datum = extract_sample(self._data[self._cur], self._mean,
self._resize)
else:
datum = self._data[self._cur]
# start parsing labels
label_elems = parse_label(self._label[self._cur])
label = np.zeros(self._label_dim)
if not self._multilabel:
label[0] = label_elems[0]
else:
for i in label_elems:
label[i] = 1
self._cur = (self._cur + 1) % self._sample_count
return datum, label
def get_a_datum(self):
if self._compressed:
datum = extract_sample(
self._data[self._cur], self._mean, self._resize)
else:
datum = self._data[self._cur]
# start parsing labels
label_elems = parse_label(self._label[self._cur])
label = np.zeros(self._label_dim)
if not self._multilabel:
label[0] = label_elems[0]
else:
for i in label_elems:
label[i] = 1
self._cur = (self._cur + 1) % self._sample_count
return datum, label