mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-06 12:20:52 +01:00
27c7158166
Summary: There is a module called `2to3` which you can target for future specifically to remove these, the directory of `caffe2` has the most redundant imports: ```2to3 -f future -w caffe2``` Pull Request resolved: https://github.com/pytorch/pytorch/pull/45033 Reviewed By: seemethere Differential Revision: D23808648 Pulled By: bugra fbshipit-source-id: 38971900f0fe43ab44a9168e57f2307580d36a38
85 lines
2.7 KiB
Python
85 lines
2.7 KiB
Python
|
|
|
|
|
|
|
|
|
|
from caffe2.python import core
|
|
from hypothesis import given
|
|
import caffe2.python.hypothesis_test_util as hu
|
|
import hypothesis.strategies as st
|
|
import numpy as np
|
|
|
|
|
|
def calculate_ap(predictions, labels):
|
|
N, D = predictions.shape
|
|
ap = np.zeros(D)
|
|
num_range = np.arange((N), dtype=np.float32) + 1
|
|
for k in range(D):
|
|
scores = predictions[:N, k]
|
|
label = labels[:N, k]
|
|
sortind = np.argsort(-scores, kind='mergesort')
|
|
truth = label[sortind]
|
|
precision = np.cumsum(truth) / num_range
|
|
ap[k] = precision[truth.astype(np.bool)].sum() / max(1, truth.sum())
|
|
return ap
|
|
|
|
|
|
class TestAPMeterOps(hu.HypothesisTestCase):
|
|
@given(predictions=hu.arrays(dims=[10, 3],
|
|
elements=hu.floats(allow_nan=False,
|
|
allow_infinity=False,
|
|
min_value=0.1,
|
|
max_value=1)),
|
|
labels=hu.arrays(dims=[10, 3],
|
|
dtype=np.int32,
|
|
elements=st.integers(min_value=0,
|
|
max_value=1)),
|
|
**hu.gcs_cpu_only)
|
|
def test_average_precision(self, predictions, labels, gc, dc):
|
|
op = core.CreateOperator(
|
|
"APMeter",
|
|
["predictions", "labels"],
|
|
["AP"],
|
|
buffer_size=10,
|
|
)
|
|
|
|
def op_ref(predictions, labels):
|
|
ap = calculate_ap(predictions, labels)
|
|
return (ap, )
|
|
|
|
self.assertReferenceChecks(
|
|
device_option=gc,
|
|
op=op,
|
|
inputs=[predictions, labels],
|
|
reference=op_ref)
|
|
|
|
@given(predictions=hu.arrays(dims=[10, 3],
|
|
elements=hu.floats(allow_nan=False,
|
|
allow_infinity=False,
|
|
min_value=0.1,
|
|
max_value=1)),
|
|
labels=hu.arrays(dims=[10, 3],
|
|
dtype=np.int32,
|
|
elements=st.integers(min_value=0,
|
|
max_value=1)),
|
|
**hu.gcs_cpu_only)
|
|
def test_average_precision_small_buffer(self, predictions, labels, gc, dc):
|
|
op_small_buffer = core.CreateOperator(
|
|
"APMeter",
|
|
["predictions", "labels"],
|
|
["AP"],
|
|
buffer_size=5,
|
|
)
|
|
|
|
def op_ref(predictions, labels):
|
|
# We can only hold the last 5 in the buffer
|
|
ap = calculate_ap(predictions[5:], labels[5:])
|
|
return (ap, )
|
|
|
|
self.assertReferenceChecks(
|
|
device_option=gc,
|
|
op=op_small_buffer,
|
|
inputs=[predictions, labels],
|
|
reference=op_ref
|
|
)
|