@attr.slow
def test_call_cpu(self):
self.check_call()
@attr.gpu
@attr.slow
def test_call_gpu(self):
self.link.to_gpu()
self.check_call()
@testing.parameterize(*testing.product({
'model': [ResNet50, ResNet101, ResNet152],
'n_class': [None, 500, 1000],
'pretrained_model': ['imagenet'],
'mean': [None, np.random.uniform((3, 1, 1)).astype(np.float32)],
'arch': ['he', 'fb'],
}))
class TestResNetPretrained(unittest.TestCase):
@attr.slow
def test_pretrained(self):
kwargs = {
'n_class': self.n_class,
'pretrained_model': self.pretrained_model,
'mean': self.mean,
'arch': self.arch,
}
if self.pretrained_model == 'imagenet':
valid = self.n_class in {None, 1000}
self.assertEqual(features.dtype, np.float32)
@attr.slow
def test_call_cpu(self):
self.check_call()
@attr.gpu
@attr.slow
def test_call_gpu(self):
self.link.to_gpu()
self.check_call()
@testing.parameterize(*testing.product({
'model': [SEResNeXt50, SEResNeXt101],
'n_class': [None, 500, 1000],
'pretrained_model': ['imagenet'],
'mean': [None, np.random.uniform((3, 1, 1)).astype(np.float32)],
}))
class TestSEResNeXtPretrained(unittest.TestCase):
@attr.slow
def test_pretrained(self):
kwargs = {
'n_class': self.n_class,
'pretrained_model': self.pretrained_model,
'mean': self.mean,
}
if self.pretrained_model == 'imagenet':
valid = self.n_class in {None, 1000}
@attr.slow
def test_call_cpu(self):
self.check_call()
@attr.gpu
@attr.slow
def test_call_gpu(self):
self.link.to_gpu()
self.check_call()
@testing.parameterize(*testing.product({
'model': [MobileNetV2],
'n_class': [None, 500, 1001],
'pretrained_model': ['imagenet'],
'mean': [None, np.random.uniform((3, 1, 1)).astype(np.float32)],
'arch': ['tf'],
}))
class TestMobileNetPretrained(unittest.TestCase):
@attr.slow
def test_pretrained(self):
kwargs = {
'n_class': self.n_class,
'pretrained_model': self.pretrained_model,
'mean': self.mean,
'arch': self.arch,
}
if self.pretrained_model == 'imagenet':
valid = self.n_class in {None, 1001}
from __future__ import division
import math
import numpy as np
import unittest
from chainercv.utils import testing
from chainercv.utils import tile_images
@testing.parameterize(*testing.product({
'fill': [128, (104, 117, 123),
np.random.uniform(255, size=(3, 1, 1))],
'pad': [0, 1, 2, 3, (3, 5), (5, 2)]
}))
class TestTileImages(unittest.TestCase):
def test_tile_images(self):
B = np.random.randint(10, 20)
n_col = np.random.randint(2, 5)
H = 30
W = 40
imgs = np.random.uniform(255, size=(B, 3, H, W))
tile = tile_images(imgs, n_col, self.pad, fill=self.fill)
if isinstance(self.pad, int):
pad_y = self.pad
pad_x = self.pad
else:
pad_y, pad_x = self.pad
n_row = int(math.ceil(B / n_col))
self.assertTrue(n_col >= 1 and n_row >= 1)