def test_zero_length_target(etype):
pytest.importorskip('torch')
args = make_arg(etype=etype)
import logging
logging.basicConfig(
level=logging.DEBUG,
format='%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s'
)
import e2e_asr_attctc as ch
import e2e_asr_attctc_th as th
ch_model = ch.E2E(40, 5, args)
ch_model.cleargrads()
th_model = th.E2E(40, 5, args)
data = [("aaa",
dict(feat=numpy.random.randn(200, 40).astype(numpy.float32),
tokenid="1")),
("bbb",
dict(feat=numpy.random.randn(100, 40).astype(numpy.float32),
tokenid="")),
("cc",
dict(feat=numpy.random.randn(100, 40).astype(numpy.float32),
tokenid="1 2"))]
ch_ctc, ch_att, ch_acc = ch_model(data)
th_ctc, th_att, th_acc = th_model(data)
def test_loss_and_ctc_grad(etype):
pytest.importorskip('torch')
args = make_arg(etype=etype)
import logging
logging.basicConfig(
level=logging.DEBUG, format='%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s')
import e2e_asr_attctc as ch
import e2e_asr_attctc_th as th
ch_model = ch.E2E(40, 5, args)
ch_model.cleargrads()
th_model = th.E2E(40, 5, args)
const = 1e-4
init_torch_weight_const(th_model, const)
init_chainer_weight_const(ch_model, const)
out_data = "1 2 3 4"
data = [
("aaa", dict(feat=numpy.random.randn(200, 40).astype(
numpy.float32), tokenid=out_data)),
("bbb", dict(feat=numpy.random.randn(100, 40).astype(
numpy.float32), tokenid=out_data)),
("cc", dict(feat=numpy.random.randn(100, 40).astype(
numpy.float32), tokenid=out_data))
]
ch_ctc, ch_att, ch_acc = ch_model(data)
th_ctc, th_att, th_acc = th_model(data)
# test masking
ch_ench = ch_model.att.pre_compute_enc_h.data
th_ench = th_model.att.pre_compute_enc_h.data.numpy()
numpy.testing.assert_equal(ch_ench == 0.0, th_ench == 0.0)
# test loss with constant weights (1.0) and bias (0.0) except for foget-bias (1.0)
numpy.testing.assert_allclose(ch_ctc.data, th_ctc.data.numpy())
numpy.testing.assert_allclose(ch_att.data, th_att.data.numpy())
# test ctc grads
ch_ctc.backward()
th_ctc.backward()
numpy.testing.assert_allclose(ch_model.ctc.ctc_lo.W.grad,
th_model.ctc.ctc_lo.weight.grad.data.numpy(), 1e-7, 1e-8)
numpy.testing.assert_allclose(ch_model.ctc.ctc_lo.b.grad,
th_model.ctc.ctc_lo.bias.grad.data.numpy(), 1e-5, 1e-6)
# test cross-entropy grads
ch_model.cleargrads()
th_model.zero_grad()
ch_ctc, ch_att, ch_acc = ch_model(data)
th_ctc, th_att, th_acc = th_model(data)
ch_att.backward()
th_att.backward()
numpy.testing.assert_allclose(ch_model.dec.output.W.grad,
th_model.dec.output.weight.grad.data.numpy(), 1e-7, 1e-8)
numpy.testing.assert_allclose(ch_model.dec.output.b.grad,
th_model.dec.output.bias.grad.data.numpy(), 1e-5, 1e-6)
def _propagate(ctc_type):
args = make_arg(ctc_type=ctc_type)
numpy.random.seed(0)
model = ch.E2E(40, 5, args)
ch_ctc, _, _ = model(data)
ch_ctc.backward()
W_grad = model.ctc.ctc_lo.W.grad
b_grad = model.ctc.ctc_lo.b.grad
return ch_ctc.data, W_grad, b_grad
