def __init__(self):
self.ps = U.Params(params).init_comps()
self.pre = None
self.post = None
i = torch.constant([0.0] * (4 * 10), shape=(4, 10))
self.src_b = torch.Variable(initial_value=i)
i = torch.constant([0.0] * (4 * 10), shape=(4, 10))
self.mem_b = torch.Variable(initial_value=i)
def main(_):
ps = utils.Params(params).init_comps()
ds = dset_for(ps, TRAIN)
# with T.distribute.MirroredStrategy().scope():
mdl = model_for(ps, compiled=True)
mdl.train_on_batch(ds)
mp = pth.Path.cwd() / ps.dir_model / ps.model
assert tf.get_checkpoint_state(str(mp))
mdl.load_weights(str(mp / TRAIN))
c = tf.Checkpoint(model=mdl, optimizer=ps.optimizer)
c.restore(str(mp / TRAIN)).expect_partial() # .assert_consumed()
for n, s in tf.list_variables(str(mp)):
print(n)
mp2 = pth.Path.cwd() / ps.dir_model / "mnist_2"
print("saving...")
c.save(str(mp2 / TRAIN))
for n, s in tf.list_variables(str(mp2)):
print(n)
assert tf.get_checkpoint_state(str(mp2))
mdl.load_weights(str(mp2 / "train-1"))
PAD=0,
brackets=None,
dim_embed=4,
dim_hidden=8,
one_hot=None,
num_toks=16,
num_types=4,
len_src=3,
len_tgt=3,
pos_max_len=None,
pos_max=1.0e4,
pos_min=1.0,
pos_start=0,
)
ps = U.Params(params).init_comps()
def test_tokembed():
e = TokEmbed(ps)
e.build((1, 5))
src = torch.constant([1, 2, 0, 3, 0], shape=(1, 5))
e.call(src)
ps.one_hot = True
e = TokEmbed(ps)
e.build((1, 5))
e.call(src)
def test_w_grad():
e = TokEmbed(ps)
def load_params():
f = "channels_first" if T.test.is_built_with_cuda() else "channels_last"
return U.Params(_params, data_format=F.FLAGS.data_format or f)