-
Notifications
You must be signed in to change notification settings - Fork 388
/
roc.py
174 lines (152 loc) · 7.15 KB
/
roc.py
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
163
164
165
166
167
168
169
170
171
172
173
174
# Copyright The PyTorch Lightning team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import Any, Callable, List, Optional, Tuple, Union
import torch
from torch import Tensor
from torchmetrics.functional.classification.roc import _roc_compute, _roc_update
from torchmetrics.metric import Metric
from torchmetrics.utilities import rank_zero_warn
class ROC(Metric):
"""Computes the Receiver Operating Characteristic (ROC). Works for both binary, multiclass and multilabel
problems. In the case of multiclass, the values will be calculated based on a one-vs-the-rest approach.
Forward accepts
- ``preds`` (float tensor): ``(N, ...)`` (binary) or ``(N, C, ...)`` (multiclass/multilabel) tensor
with probabilities, where C is the number of classes/labels.
- ``target`` (long tensor): ``(N, ...)`` or ``(N, C, ...)`` with integer labels
.. note::
If either the positive class or negative class is completly missing in the target tensor,
the roc values are not well defined in this case and a tensor of zeros will be returned (either fpr
or tpr depending on what class is missing) together with an warning.
Args:
num_classes: integer with number of classes for multi-label and multiclass problems.
Should be set to ``None`` for binary problems
pos_label: integer determining the positive class. Default is ``None``
which for binary problem is translate to 1. For multiclass problems
this argument should not be set as we iteratively change it in the
range [0,num_classes-1]
compute_on_step:
Forward only calls ``update()`` and return None if this is set to False.
dist_sync_on_step:
Synchronize metric state across processes at each ``forward()``
before returning the value at the step.
process_group:
Specify the process group on which synchronization is called.
dist_sync_fn:
Callback that performs the allgather operation on the metric state. When ``None``, DDP
will be used to perform the allgather
Example (binary case):
>>> from torchmetrics import ROC
>>> pred = torch.tensor([0, 1, 2, 3])
>>> target = torch.tensor([0, 1, 1, 1])
>>> roc = ROC(pos_label=1)
>>> fpr, tpr, thresholds = roc(pred, target)
>>> fpr
tensor([0., 0., 0., 0., 1.])
>>> tpr
tensor([0.0000, 0.3333, 0.6667, 1.0000, 1.0000])
>>> thresholds
tensor([4, 3, 2, 1, 0])
Example (multiclass case):
>>> pred = torch.tensor([[0.75, 0.05, 0.05, 0.05],
... [0.05, 0.75, 0.05, 0.05],
... [0.05, 0.05, 0.75, 0.05],
... [0.05, 0.05, 0.05, 0.75]])
>>> target = torch.tensor([0, 1, 3, 2])
>>> roc = ROC(num_classes=4)
>>> fpr, tpr, thresholds = roc(pred, target)
>>> fpr
[tensor([0., 0., 1.]), tensor([0., 0., 1.]), tensor([0.0000, 0.3333, 1.0000]), tensor([0.0000, 0.3333, 1.0000])]
>>> tpr
[tensor([0., 1., 1.]), tensor([0., 1., 1.]), tensor([0., 0., 1.]), tensor([0., 0., 1.])]
>>> thresholds
[tensor([1.7500, 0.7500, 0.0500]),
tensor([1.7500, 0.7500, 0.0500]),
tensor([1.7500, 0.7500, 0.0500]),
tensor([1.7500, 0.7500, 0.0500])]
Example (multilabel case):
>>> pred = torch.tensor([[0.8191, 0.3680, 0.1138],
... [0.3584, 0.7576, 0.1183],
... [0.2286, 0.3468, 0.1338],
... [0.8603, 0.0745, 0.1837]])
>>> target = torch.tensor([[1, 1, 0], [0, 1, 0], [0, 0, 0], [0, 1, 1]])
>>> roc = ROC(num_classes=3, pos_label=1)
>>> fpr, tpr, thresholds = roc(pred, target)
>>> fpr
[tensor([0.0000, 0.3333, 0.3333, 0.6667, 1.0000]),
tensor([0., 0., 0., 1., 1.]),
tensor([0.0000, 0.0000, 0.3333, 0.6667, 1.0000])]
>>> tpr
[tensor([0., 0., 1., 1., 1.]),
tensor([0.0000, 0.3333, 0.6667, 0.6667, 1.0000]),
tensor([0., 1., 1., 1., 1.])]
>>> thresholds
[tensor([1.8603, 0.8603, 0.8191, 0.3584, 0.2286]),
tensor([1.7576, 0.7576, 0.3680, 0.3468, 0.0745]),
tensor([1.1837, 0.1837, 0.1338, 0.1183, 0.1138])]
"""
is_differentiable = False
preds: List[Tensor]
target: List[Tensor]
def __init__(
self,
num_classes: Optional[int] = None,
pos_label: Optional[int] = None,
compute_on_step: bool = True,
dist_sync_on_step: bool = False,
process_group: Optional[Any] = None,
dist_sync_fn: Callable = None,
) -> None:
super().__init__(
compute_on_step=compute_on_step,
dist_sync_on_step=dist_sync_on_step,
process_group=process_group,
dist_sync_fn=dist_sync_fn,
)
self.num_classes = num_classes
self.pos_label = pos_label
self.add_state("preds", default=[], dist_reduce_fx=None)
self.add_state("target", default=[], dist_reduce_fx=None)
rank_zero_warn(
"Metric `ROC` will save all targets and predictions in buffer."
" For large datasets this may lead to large memory footprint."
)
def update(self, preds: Tensor, target: Tensor) -> None: # type: ignore
"""Update state with predictions and targets.
Args:
preds: Predictions from model
target: Ground truth values
"""
preds, target, num_classes, pos_label = _roc_update(preds, target, self.num_classes, self.pos_label)
self.preds.append(preds)
self.target.append(target)
self.num_classes = num_classes
self.pos_label = pos_label
def compute(self) -> Union[Tuple[Tensor, Tensor, Tensor], Tuple[List[Tensor], List[Tensor], List[Tensor]]]:
"""Compute the receiver operating characteristic.
Returns:
3-element tuple containing
fpr:
tensor with false positive rates.
If multiclass, this is a list of such tensors, one for each class.
tpr:
tensor with true positive rates.
If multiclass, this is a list of such tensors, one for each class.
thresholds:
thresholds used for computing false- and true postive rates
"""
preds = torch.cat(self.preds, dim=0)
target = torch.cat(self.target, dim=0)
if not self.num_classes:
raise ValueError(f"`num_classes` bas to be positive number, but got {self.num_classes}")
return _roc_compute(preds, target, self.num_classes, self.pos_label)