def test_sortagrad_trainable_with_batch_bins(module):
args = make_arg(sortagrad=1)
idim = 20
odim = 5
dummy_json = make_dummy_json_st(
4, [10, 20], [10, 20], [10, 20], idim=idim, odim=odim
)
if module == "pytorch":
import espnet.nets.pytorch_backend.e2e_st as m
else:
raise NotImplementedError
batch_elems = 2000
batchset = make_batchset(dummy_json, batch_bins=batch_elems, shortest_first=True)
for batch in batchset:
n = 0
for uttid, info in batch:
ilen = int(info["input"][0]["shape"][0])
olen = int(info["output"][0]["shape"][0])
n += ilen * idim + olen * odim
assert olen < batch_elems
model = m.E2E(20, 5, args)
for batch in batchset:
loss = model(*convert_batch(batch, module, idim=20, odim=5))
if isinstance(loss, tuple):
# chainer return several values as tuple
loss[0].backward() # trainable
else:
loss.backward() # trainable
with torch.no_grad(), chainer.no_backprop_mode():
in_data = np.random.randn(100, 20)
model.translate(in_data, args, args.char_list)
def test_gradient_noise_injection(module):
args = make_arg(grad_noise=True)
args_org = make_arg()
dummy_json = make_dummy_json_st(2, [10, 20], [10, 20], [10, 20], idim=20, odim=5)
if module == "pytorch":
import espnet.nets.pytorch_backend.e2e_st as m
else:
raise NotImplementedError
batchset = make_batchset(dummy_json, 2, 2**10, 2**10, shortest_first=True)
model = m.E2E(20, 5, args)
model_org = m.E2E(20, 5, args_org)
for batch in batchset:
loss = model(*convert_batch(batch, module, idim=20, odim=5))
loss_org = model_org(*convert_batch(batch, module, idim=20, odim=5))
loss.backward()
grad = [param.grad for param in model.parameters()][10]
loss_org.backward()
grad_org = [param.grad for param in model_org.parameters()][10]
assert grad[0] != grad_org[0]
def test_sortagrad_trainable(module):
args = make_arg(sortagrad=1)
dummy_json = make_dummy_json_st(4, [10, 20], [10, 20], [10, 20], idim=20, odim=5)
if module == "pytorch":
import espnet.nets.pytorch_backend.e2e_st as m
else:
raise NotImplementedError
batchset = make_batchset(dummy_json, 2, 2**10, 2**10, shortest_first=True)
model = m.E2E(20, 5, args)
for batch in batchset:
loss = model(*convert_batch(batch, module, idim=20, odim=5))
if isinstance(loss, tuple):
# chainer return several values as tuple
loss[0].backward() # trainable
else:
loss.backward() # trainable
with torch.no_grad(), chainer.no_backprop_mode():
in_data = np.random.randn(50, 20)
model.translate(in_data, args, args.char_list)
def test_sortagrad_trainable_with_batch_frames(module):
args = make_arg(sortagrad=1)
idim = 20
odim = 5
dummy_json = make_dummy_json_st(4, [10, 20], [10, 20], [10, 20],
idim=idim,
odim=odim)
if module == "pytorch":
import espnet.nets.pytorch_backend.e2e_st as m
else:
raise NotImplementedError
batch_frames_in = 50
batch_frames_out = 50
batchset = make_batchset(dummy_json,
batch_frames_in=batch_frames_in,
batch_frames_out=batch_frames_out,
shortest_first=True)
for batch in batchset:
i = 0
o = 0
for uttid, info in batch:
i += int(info['input'][0]['shape'][0])
o += int(info['output'][0]['shape'][0])
assert i <= batch_frames_in
assert o <= batch_frames_out
model = m.E2E(20, 5, args)
for batch in batchset:
loss = model(*convert_batch(batch, module, idim=20, odim=5))
if isinstance(loss, tuple):
# chainer return several values as tuple
loss[0].backward() # trainable
else:
loss.backward() # trainable
with torch.no_grad(), chainer.no_backprop_mode():
in_data = np.random.randn(100, 20)
model.translate(in_data, args, args.char_list)