def main():
import numpy as np
np.random.seed(314)
x = np.random.rand(12, 6, 4).astype(np.float32)
testtools.generate_testcase(Size(), [x])
def main():
import numpy as np
np.random.seed(314)
x = np.random.rand(5, 7).astype(np.float32)
y = np.random.rand(7, 4).astype(np.float32)
testtools.generate_testcase(Matmul, [x, y])
def main():
np.random.seed(314)
testtools.generate_testcase(Len(), [np.random.rand(3, 5, 4)],
subname='basic')
testtools.generate_testcase(LenList(), [[np.array(x) for x in [3, 5, 4]]],
subname='list')
def main():
import numpy as np
np.random.seed(314)
eprojs = 3
dunits = 4
att_dim = 5
batch_size = 3
sequence_length = 4
num_vocabs = 10
model_fn = lambda: AttDot(eprojs, dunits, att_dim)
labels, ilens = sequence_utils.gen_random_sequence(batch_size,
sequence_length,
num_vocabs)
xs = []
for l in ilens:
xs.append(np.random.rand(l, eprojs).astype(np.float32))
# Check if our modification is valid.
expected = model_fn().original(xs, None, None)
actual = model_fn().forward(xs, None, None)
for e, a in zip(expected, actual):
assert np.allclose(e.array, a.array)
testtools.generate_testcase(model_fn, [xs, None, None])
z = np.random.rand(batch_size, dunits).astype(np.float32)
testtools.generate_testcase(
lambda: AttDotBackprop(eprojs, dunits, att_dim), [xs, z, None],
backprop=True)
def main():
import numpy as np
np.random.seed(314)
idim = 5
elayers = 2
cdim = 3
hdim = 7
batch_size = 3
sequence_length = 4
num_vocabs = 10
model = BLSTM(idim, elayers, cdim, hdim, 0)
labels, ilens = sequence_utils.gen_random_sequence(batch_size,
sequence_length,
num_vocabs)
xs = []
for l in ilens:
xs.append(np.random.rand(l, idim).astype(dtype=np.float32))
# Check if our modification is valid.
expected = model.original(xs, ilens)
actual = model.forward(xs, ilens)
for e, a in zip(expected[0], actual[0]):
assert np.allclose(e.array, a.array)
assert np.allclose(expected[1], actual[1])
testtools.generate_testcase(model, [xs, ilens])
testtools.generate_testcase(BLSTMBackprop(idim, elayers, cdim, hdim, 0),
[xs, ilens],
backprop=True)
def main():
import numpy as np
np.random.seed(314)
model = ExpandDims()
x = np.random.rand(6, 4).astype(np.float32) - 0.5
testtools.generate_testcase(model, [x])
def main():
import numpy as np
np.random.seed(43)
batch_size = 3
in_size = 7
out_size = 4
def model_fn():
lstm = StatelessLSTM(in_size, out_size)
return lstm
c = np.random.rand(batch_size, out_size).astype(np.float32)
h = np.random.rand(batch_size, out_size).astype(np.float32)
x = np.random.rand(batch_size, in_size).astype(np.float32)
model = model_fn()
# Check if our modification is valid.
expected = model.original(c, h, x)
actual = model.forward(c, h, x)
for e, a in zip(expected, actual):
assert np.allclose(e.array, a.array)
testtools.generate_testcase(model_fn(), [c, h, x])
# TODO (hamaji): support func
# testtools.generate_testcase(model_fn, [c, h, x])
def model_fn():
lstm = StatelessLSTMBackprop(in_size, out_size)
return lstm
testtools.generate_testcase(model_fn(), [c, h, x], backprop=True)
def main():
import numpy as np
np.random.seed(314)
idim = 5
elayers = 2
cdim = 3
hdim = 7
batch_size = 3
sequence_length = 4
num_vocabs = 10
labels, ilens = sequence_utils.gen_random_sequence(batch_size,
sequence_length,
num_vocabs)
xs = []
for l in ilens:
xs.append(np.random.rand(l, idim).astype(dtype=np.float32))
testtools.generate_testcase(VGG2L(1), [xs, ilens], subname='VGGL')
# TODO (hamaji): support lambda
#testtools.generate_testcase(lambda: VGG2L(1), [xs, ilens], subname='VGGL_lambda')
testtools.generate_testcase(VGG2LBackprop(1), [xs, ilens],
backprop=True,
subname='VGGL_backprop')
def main():
model = Tanh()
np.random.seed(314)
x = np.random.rand(6, 4).astype(np.float32)
testtools.generate_testcase(model, [x])
def main():
np.random.seed(314)
model = GoogLeNet() # 224
v = np.random.rand(1, 3, 227, 227).astype(np.float32)
t = np.random.randint(1000, size=1)
testtools.generate_testcase(model, [v, t])
def main():
model = A()
x = np.random.rand(6, 4, 2, 7).astype(np.float32)
testtools.generate_testcase(model, [x])
testtools.generate_testcase(Self(), [x], subname='self')
def main():
import numpy as np
np.random.seed(314)
eprojs = 3
dunits = 4
att_dim = 5
batch_size = 3
sequence_length = 4
num_vocabs = 10
aconv_chans = 7
aconv_filts = 6
model_fn = lambda: AttLoc(eprojs, dunits, att_dim, aconv_chans, aconv_filts
)
labels, ilens = sequence_utils.gen_random_sequence(batch_size,
sequence_length,
num_vocabs)
xs = []
for l in ilens:
xs.append(np.random.rand(l, eprojs).astype(dtype=np.float32))
# Check if our modification is valid.
model = model_fn()
expected = model.original(xs, None, None)
model.reset()
actual = model.forward(xs, None, None)
for e, a in zip(expected, actual):
assert np.allclose(e.array, a.array)
testtools.generate_testcase(model_fn, [xs, None, None])
def main():
v = np.random.rand(7, 4, 2).astype(np.float32)
w = np.random.rand(7, 3, 2).astype(np.float32)
testtools.generate_testcase(ConcatTuple, [v, w])
testtools.generate_testcase(ConcatList, [v, w], subname='list')
def main():
np.random.seed(314)
n_fg_class = 80
base = ResNet50(n_class=n_fg_class, arch='he')
base.pick = ('res2', 'res3', 'res4', 'res5')
base.pool1 = lambda x: F.max_pooling_2d(
x, 3, stride=2, pad=1, cover_all=False)
base.remove_unused()
extractor = FPN(base, len(base.pick),
(1 / 4, 1 / 8, 1 / 16, 1 / 32, 1 / 64))
return_values = ['bboxes', 'labels', 'scores']
min_size = 800
max_size = 1333
model = FasterRCNN(extractor=extractor,
rpn=RPN(extractor.scales),
bbox_head=BboxHead(n_fg_class + 1, extractor.scales),
mask_head=MaskHead(n_fg_class + 1, extractor.scales),
return_values=return_values,
min_size=min_size,
max_size=max_size)
bsize = 2
v = np.random.rand(bsize, 3, 224, 224).astype(np.float32)
# testtools.generate_testcase(base, [v], 'base')
# testtools.generate_testcase(extractor, [v], 'extractor')
testtools.generate_testcase(model, [v], 'faster_rcnn')
def main():
np.random.seed(314)
a1 = np.random.rand(6, 2, 3).astype(np.float32)
a2 = np.random.rand(6, 2, 3).astype(np.float32)
testtools.generate_testcase(Minimum(), [a1, a2])
testtools.generate_testcase(MinimumNumpy(), [a1, a2], subname='np')
def main():
model = A()
v = np.random.rand(3, 5).astype(np.float32)
w = np.random.rand(3, 5).astype(np.float32)
testtools.generate_testcase(model, [v, w])
def main():
np.random.seed(314)
model = Alex(shrink_ratio=23)
v = np.random.rand(5, 3, 227, 227).astype(np.float32)
t = np.random.randint(1000, size=5)
testtools.generate_testcase(model, [v, t])
def gen_test(model_fn, subname=None):
model = model_fn()
# Check if our modification is valid.
expected = model.original(xs, ilens, ys)
actual = model.forward(xs, ilens, ys)
assert np.allclose(expected.array, actual.array)
testtools.generate_testcase(model_fn, [xs, ilens, ys], subname=subname)
def main():
np.random.seed(314)
v = np.random.rand(3, 7).astype(np.float32)
model = A()
result = model(v)
testtools.generate_testcase(model, [v])
def main():
out_n = 2
batch_size = 1
model = A()
v = np.random.rand(batch_size, out_n).astype(np.float32)
w = np.random.randint(out_n, size=batch_size)
testtools.generate_testcase(model, [v, w])
def gen(output, recipe, bwd=True, use_gpu=False):
import testtools
test_args.get_test_args([output, '--allow-unused-params'])
(idim, odim, args), (xs, ilens, ys) = recipe
testtools.generate_testcase(lambda: E2E(idim, odim, args), [xs, ilens, ys],
backprop=bwd,
use_gpu=use_gpu)
def main():
model = A()
np.random.seed(123)
x = np.random.rand(2, 20, 15, 17).astype(np.float32)
testtools.generate_testcase(model, [x])
testtools.generate_testcase(SingleParam(), [x], subname='single_param')
def main():
import numpy as np
np.random.seed(314)
model = A()
x = np.random.rand(12, 6, 4).astype(np.float32)
p = np.int64(3)
testtools.generate_testcase(model, [x, p])
def main():
import numpy as np
np.random.seed(314)
model = A()
x = np.random.rand(5, 7).astype(np.float32)
x = [x]
testtools.generate_testcase(model, x)
def main():
import numpy as np
np.random.seed(12)
model = A()
ps = [3, 1, 4, 1, 5, 9, 2]
testtools.generate_testcase(model, [ps])
def main():
import numpy as np
np.random.seed(314)
model = A()
v = np.random.rand(2, 3, 5, 5).astype(np.float32)
testtools.generate_testcase(model, [v])
def main():
import numpy as np
np.random.seed(43)
eprojs = 3
dunits = 4
att_dim = 5
batch_size = 3
sequence_length = 4
num_vocabs = 10
dlayers = 2
odim = 11
sos = odim - 1
eos = odim - 1
aconv_chans = 7
aconv_filts = 6
labels, ilens = sequence_utils.gen_random_sequence(batch_size,
sequence_length,
num_vocabs)
hs = []
for l in ilens:
hs.append(np.random.rand(l, eprojs).astype(dtype=np.float32))
ys, ilens = sequence_utils.gen_random_sequence(batch_size, sequence_length,
odim)
def gen_test(model_fn, subname=None):
model = model_fn()
# Check if our modification is valid.
expected, _ = model.original(hs, ys)
actual = model.forward(hs, ys)
assert np.allclose(expected.array, actual.array)
testtools.generate_testcase(model_fn, [hs, ys], subname=subname)
def model_fn():
# att = AttDot(eprojs, dunits, att_dim)
# dec = Decoder(eprojs, odim, dlayers, dunits, sos, eos, att)
dec = Decoder(eprojs, odim, dlayers, dunits, sos, eos, att_dim)
return dec
gen_test(model_fn)
testtools.generate_testcase(model_fn, [hs, ys], backprop=True)
def model_fn():
dec = Decoder(eprojs, odim, dlayers, dunits, sos, eos, att_dim,
aconv_chans, aconv_filts)
return dec
gen_test(model_fn, subname='attloc')
testtools.generate_testcase(model_fn, [hs, ys],
subname='attloc',
backprop=True)
def main():
np.random.seed(314)
x = np.random.rand(6, 4, 1).astype(np.float32) - 0.5
testtools.generate_testcase(BroadcastTo(), [x], subname='basic')
x = np.random.rand(6, 3).astype(np.float32) - 0.5
testtools.generate_testcase(BroadcastToBackprop(), [x],
backprop=True,
subname='with_backprop')
def main():
np.random.seed(314)
out_n = 4
batch_size = 100
model = MLP(8, out_n)
v = np.random.rand(batch_size, 3).astype(np.float32)
w = np.random.randint(out_n, size=batch_size)
testtools.generate_testcase(model, [v, w])
def main():
np.random.seed(314)
model = FasterRCNNFPNResNet50(n_fg_class=80)
bsize = 2
v = np.random.rand(bsize, 3, 224, 224).astype(np.float32)
testtools.generate_testcase(model, [v])
