Spaces:
Runtime error
Runtime error
File size: 5,944 Bytes
ac6e446 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 |
# vim: expandtab:ts=4:sw=4
import numpy as np
import sys
import torch
def _pdist(a, b):
"""Compute pair-wise squared distance between points in `a` and `b`.
Parameters
----------
a : array_like
An NxM matrix of N samples of dimensionality M.
b : array_like
An LxM matrix of L samples of dimensionality M.
Returns
-------
ndarray
Returns a matrix of size len(a), len(b) such that eleement (i, j)
contains the squared distance between `a[i]` and `b[j]`.
"""
a, b = np.asarray(a), np.asarray(b)
if len(a) == 0 or len(b) == 0:
return np.zeros((len(a), len(b)))
a2, b2 = np.square(a).sum(axis=1), np.square(b).sum(axis=1)
r2 = -2. * np.dot(a, b.T) + a2[:, None] + b2[None, :]
r2 = np.clip(r2, 0., float(np.inf))
return r2
def _cosine_distance(a, b, data_is_normalized=False):
"""Compute pair-wise cosine distance between points in `a` and `b`.
Parameters
----------
a : array_like
An NxM matrix of N samples of dimensionality M.
b : array_like
An LxM matrix of L samples of dimensionality M.
data_is_normalized : Optional[bool]
If True, assumes rows in a and b are unit length vectors.
Otherwise, a and b are explicitly normalized to lenght 1.
Returns
-------
ndarray
Returns a matrix of size len(a), len(b) such that eleement (i, j)
contains the squared distance between `a[i]` and `b[j]`.
"""
if not data_is_normalized:
a = np.asarray(a) / np.linalg.norm(a, axis=1, keepdims=True)
b = np.asarray(b) / np.linalg.norm(b, axis=1, keepdims=True)
return 1. - np.dot(a, b.T)
def _nn_euclidean_distance(x, y):
""" Helper function for nearest neighbor distance metric (Euclidean).
Parameters
----------
x : ndarray
A matrix of N row-vectors (sample points).
y : ndarray
A matrix of M row-vectors (query points).
Returns
-------
ndarray
A vector of length M that contains for each entry in `y` the
smallest Euclidean distance to a sample in `x`.
"""
# x_ = torch.from_numpy(np.asarray(x) / np.linalg.norm(x, axis=1, keepdims=True))
# y_ = torch.from_numpy(np.asarray(y) / np.linalg.norm(y, axis=1, keepdims=True))
distances = distances = _pdist(x, y)
return np.maximum(0.0, torch.min(distances, axis=0)[0].numpy())
def _nn_cosine_distance(x, y):
""" Helper function for nearest neighbor distance metric (cosine).
Parameters
----------
x : ndarray
A matrix of N row-vectors (sample points).
y : ndarray
A matrix of M row-vectors (query points).
Returns
-------
ndarray
A vector of length M that contains for each entry in `y` the
smallest cosine distance to a sample in `x`.
"""
x_ = torch.from_numpy(np.asarray(x))
y_ = torch.from_numpy(np.asarray(y))
distances = _cosine_distance(x_, y_)
distances = distances
return distances.min(axis=0)
class NearestNeighborDistanceMetric(object):
"""
A nearest neighbor distance metric that, for each target, returns
the closest distance to any sample that has been observed so far.
Parameters
----------
metric : str
Either "euclidean" or "cosine".
matching_threshold: float
The matching threshold. Samples with larger distance are considered an
invalid match.
budget : Optional[int]
If not None, fix samples per class to at most this number. Removes
the oldest samples when the budget is reached.
Attributes
----------
samples : Dict[int -> List[ndarray]]
A dictionary that maps from target identities to the list of samples
that have been observed so far.
"""
def __init__(self, metric, matching_threshold, budget=None):
if metric == "euclidean":
self._metric = _nn_euclidean_distance
elif metric == "cosine":
self._metric = _nn_cosine_distance
else:
raise ValueError(
"Invalid metric; must be either 'euclidean' or 'cosine'")
self.matching_threshold = matching_threshold
self.budget = budget
self.samples = {}
def partial_fit(self, features, targets, active_targets):
"""Update the distance metric with new data.
Parameters
----------
features : ndarray
An NxM matrix of N features of dimensionality M.
targets : ndarray
An integer array of associated target identities.
active_targets : List[int]
A list of targets that are currently present in the scene.
"""
for feature, target in zip(features, targets):
self.samples.setdefault(target, []).append(feature)
if self.budget is not None:
self.samples[target] = self.samples[target][-self.budget:]
self.samples = {k: self.samples[k] for k in active_targets}
def distance(self, features, targets):
"""Compute distance between features and targets.
Parameters
----------
features : ndarray
An NxM matrix of N features of dimensionality M.
targets : List[int]
A list of targets to match the given `features` against.
Returns
-------
ndarray
Returns a cost matrix of shape len(targets), len(features), where
element (i, j) contains the closest squared distance between
`targets[i]` and `features[j]`.
"""
cost_matrix = np.zeros((len(targets), len(features)))
for i, target in enumerate(targets):
cost_matrix[i, :] = self._metric(self.samples[target], features)
return cost_matrix |