def _loop(function, itr):
prev_h1, prev_h2, prev_h3 = [
np_zeros((minibatch_size, n_hid)) for i in range(3)
]
prev_kappa = np_zeros((minibatch_size, att_size))
prev_w = np_zeros((minibatch_size, n_chars))
X_mb, X_mb_mask, c_mb, c_mb_mask = next(itr)
n_cuts = len(X_mb) // cut_len + 1
partial_costs = []
for n in range(n_cuts):
start = n * cut_len
stop = (n + 1) * cut_len
if len(X_mb[start:stop]) < cut_len:
new_len = cut_len - len(X_mb) % cut_len
zeros = np.zeros((new_len, X_mb.shape[1], X_mb.shape[2]))
zeros = zeros.astype(X_mb.dtype)
mask_zeros = np.zeros((new_len, X_mb_mask.shape[1]))
mask_zeros = mask_zeros.astype(X_mb_mask.dtype)
X_mb = np.concatenate((X_mb, zeros), axis=0)
X_mb_mask = np.concatenate((X_mb_mask, mask_zeros), axis=0)
assert len(X_mb[start:stop]) == cut_len
assert len(X_mb_mask[start:stop]) == cut_len
rval = function(X_mb[start:stop], X_mb_mask[start:stop], c_mb,
c_mb_mask, prev_h1, prev_h2, prev_h3, prev_kappa,
prev_w)
current_cost = rval[0]
prev_h1, prev_h2, prev_h3 = rval[1:4]
prev_h1 = prev_h1[-1]
prev_h2 = prev_h2[-1]
prev_h3 = prev_h3[-1]
prev_kappa = rval[4][-1]
prev_w = rval[5][-1]
partial_costs.append(current_cost)
return partial_costs
def _loop(function, itr):
prev_h1, prev_h2 = [np_zeros((minibatch_size, n_hid))
for i in range(2)]
prev_kappa = np_zeros((minibatch_size, att_size))
prev_w = np_zeros((minibatch_size, n_chars))
X_mb, X_mb_mask, c_mb, c_mb_mask = next(itr)
n_cuts = len(X_mb) // cut_len + 1
partial_costs = []
for n in range(n_cuts):
start = n * cut_len
stop = (n + 1) * cut_len
if len(X_mb[start:stop]) < cut_len:
new_len = cut_len - len(X_mb) % cut_len
zeros = np.zeros((new_len, X_mb.shape[1],
X_mb.shape[2]))
zeros = zeros.astype(X_mb.dtype)
mask_zeros = np.zeros((new_len, X_mb_mask.shape[1]))
mask_zeros = mask_zeros.astype(X_mb_mask.dtype)
X_mb = np.concatenate((X_mb, zeros), axis=0)
X_mb_mask = np.concatenate((X_mb_mask, mask_zeros), axis=0)
assert len(X_mb[start:stop]) == cut_len
assert len(X_mb_mask[start:stop]) == cut_len
rval = function(X_mb[start:stop],
X_mb_mask[start:stop],
c_mb, c_mb_mask,
prev_h1, prev_h2, prev_kappa, prev_w)
current_cost = rval[0]
prev_h1, prev_h2 = rval[1:3]
prev_h1 = prev_h1[-1]
prev_h2 = prev_h2[-1]
prev_kappa = rval[3][-1]
prev_w = rval[4][-1]
partial_costs.append(current_cost)
return partial_costs
def _loop(function, itr):
prev_h1, prev_h2, prev_h3 = [np_zeros((minibatch_size, n_hid))
for i in range(3)]
X_mb, X_mb_mask, y_mb, y_mb_mask = next(itr)
n_cuts = len(X_mb) // cut_len + 1
partial_costs = []
for n in range(n_cuts):
start = n * cut_len
stop = (n + 1) * cut_len
if len(X_mb[start:stop]) < cut_len:
# skip end edge case
break
new_len = cut_len - len(X_mb) % cut_len
zeros = np.zeros((new_len, X_mb.shape[1],
X_mb.shape[2]))
zeros = zeros.astype(X_mb.dtype)
mask_zeros = np.zeros((new_len, X_mb_mask.shape[1]))
mask_zeros = mask_zeros.astype(X_mb_mask.dtype)
X_mb = np.concatenate((X_mb, zeros), axis=0)
X_mb_mask = np.concatenate((X_mb_mask, mask_zeros), axis=0)
assert len(X_mb[start:stop]) == cut_len
assert len(X_mb_mask[start:stop]) == cut_len
rval = function(X_mb[start:stop],
X_mb_mask[start:stop],
y_mb[start:stop], y_mb_mask[start:stop],
prev_h1, prev_h2, prev_h3)
current_cost = rval[0]
prev_h1, prev_h2, prev_h3 = rval[1:4]
prev_h1 = prev_h1[-1]
prev_h2 = prev_h2[-1]
prev_h3 = prev_h3[-1]
partial_costs.append(current_cost)
return partial_costs
def _loop(function, itr):
prev_h1, prev_h2, prev_h3 = [np_zeros((minibatch_size, n_hid))
for i in range(3)]
X_mb, X_mb_mask = next(itr)
# sanity check that masking code is OK
assert X_mb_mask.min() > 1E-6
n_cuts = len(X_mb) // cut_len + 1
partial_costs = []
for n in range(n_cuts):
if n % 100 == 0:
print("step %i" % n, end="")
else:
print(".", end="")
start = n * cut_len
stop = (n + 1) * cut_len
if len(X_mb[start:stop]) < cut_len:
# skip end edge case
break
rval = function(X_mb[start:stop],
X_mb_mask[start:stop],
prev_h1, prev_h2, prev_h3)
current_cost = rval[0]
prev_h1, prev_h2, prev_h3 = rval[1:4]
prev_h1 = prev_h1[-1]
prev_h2 = prev_h2[-1]
prev_h3 = prev_h3[-1]
partial_costs.append(current_cost)
print("")
return partial_costs
def _loop(function, itr):
prev_h1, prev_h2, prev_h3 = [
np_zeros((minibatch_size, n_hid)) for i in range(3)
]
X_mb, X_mb_mask = next(itr)
# sanity check that masking code is OK
assert X_mb_mask.min() > 1E-6
n_cuts = len(X_mb) // cut_len + 1
partial_costs = []
for n in range(n_cuts):
if n % 100 == 0:
print("step %i" % n, end="")
else:
print(".", end="")
start = n * cut_len
stop = (n + 1) * cut_len
if len(X_mb[start:stop]) < cut_len:
# skip end edge case
break
rval = function(X_mb[start:stop], X_mb_mask[start:stop], prev_h1,
prev_h2, prev_h3)
current_cost = rval[0]
prev_h1, prev_h2, prev_h3 = rval[1:4]
prev_h1 = prev_h1[-1]
prev_h2 = prev_h2[-1]
prev_h3 = prev_h3[-1]
partial_costs.append(current_cost)
print("")
return partial_costs
checkpoint_file = args.plot
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
train_costs = checkpoint_dict["train_costs"]
valid_costs = checkpoint_dict["valid_costs"]
plt.plot(train_costs)
plt.plot(valid_costs)
plt.savefig("costs.png")
X_mb, X_mb_mask, c_mb, c_mb_mask = next(valid_itr)
valid_itr.reset()
prev_h1, prev_h2, prev_h3 = [
np_zeros((minibatch_size, n_hid)) for i in range(3)
]
prev_kappa = np_zeros((minibatch_size, att_size))
prev_w = np_zeros((minibatch_size, n_chars))
if args.sample is not None:
predict_function = checkpoint_dict["predict_function"]
attention_function = checkpoint_dict["attention_function"]
sample_function = checkpoint_dict["sample_function"]
if args.write is not None:
sample_string = args.write
print("Sampling using sample string %s" % sample_string)
oh = dense_to_one_hot(
np.array([vocabulary[c] for c in sample_string]),
vocabulary_size)
c_mb = np.zeros(
(len(oh), minibatch_size, oh.shape[-1])).astype(c_mb.dtype)
checkpoint_file = args.plot
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
train_costs = checkpoint_dict["overall_train_costs"]
valid_costs = checkpoint_dict["overall_valid_costs"]
plt.plot(train_costs)
plt.plot(valid_costs)
plt.savefig("costs.png")
X_mb, X_mb_mask, c_mb, c_mb_mask = next(valid_itr)
valid_itr.reset()
prev_h1, prev_h2, prev_h3 = [np_zeros((minibatch_size, n_hid))
for i in range(3)]
prev_kappa = np_zeros((minibatch_size, att_size))
prev_w = np_zeros((minibatch_size, n_chars))
bias = args.bias
if args.sample is not None:
predict_function = checkpoint_dict["predict_function"]
attention_function = checkpoint_dict["attention_function"]
sample_function = checkpoint_dict["sample_function"]
if args.write is not None:
sample_string = args.write
print("Sampling using sample string %s" % sample_string)
oh = dense_to_one_hot(
np.array([vocabulary[c] for c in sample_string]),
vocabulary_size)
c_mb = np.zeros(
else:
checkpoint_file = args.plot
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
train_costs = checkpoint_dict["train_costs"]
valid_costs = checkpoint_dict["valid_costs"]
plt.plot(train_costs)
plt.plot(valid_costs)
plt.savefig("costs.png")
X_mb, X_mb_mask, c_mb, c_mb_mask = next(valid_itr)
valid_itr.reset()
prev_h1, prev_h2, prev_h3 = [np_zeros((minibatch_size, n_hid))
for i in range(3)]
prev_kappa = np_zeros((minibatch_size, att_size))
prev_w = np_zeros((minibatch_size, n_chars))
if args.sample is not None:
predict_function = checkpoint_dict["predict_function"]
attention_function = checkpoint_dict["attention_function"]
sample_function = checkpoint_dict["sample_function"]
if args.write is not None:
sample_string = args.write
print("Sampling using sample string %s" % sample_string)
oh = dense_to_one_hot(
np.array([vocabulary[c] for c in sample_string]),
vocabulary_size)
c_mb = np.zeros(
(len(oh), minibatch_size, oh.shape[-1])).astype(c_mb.dtype)
checkpoint_file = args.plot
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
train_costs = checkpoint_dict["overall_train_costs"]
valid_costs = checkpoint_dict["overall_valid_costs"]
plt.plot(train_costs)
plt.plot(valid_costs)
plt.savefig("costs.png")
X_mb, X_mb_mask, c_mb, c_mb_mask = next(train_itr)
train_itr.reset()
prev_h1, prev_h2, prev_h3 = [
np_zeros((minibatch_size, n_hid)) for i in range(3)
]
prev_kappa = np_zeros((minibatch_size, att_size))
prev_w = np_zeros((minibatch_size, n_chars))
bias = args.bias
if args.sample is not None:
predict_function = checkpoint_dict["predict_function"]
attention_function = checkpoint_dict["attention_function"]
sample_function = checkpoint_dict["sample_function"]
if args.write is not None:
sample_string = args.write
print("Sampling using sample string %s" % sample_string)
oh = dense_to_one_hot(
np.array([vocabulary[c] for c in sample_string]),
vocabulary_size)
c_mb = np.zeros(
import matplotlib.pyplot as plt
checkpoint_file = args.sample
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
train_costs = checkpoint_dict["train_costs"]
valid_costs = checkpoint_dict["valid_costs"]
plt.plot(train_costs)
plt.plot(valid_costs)
plt.savefig("costs.png")
X_mb, X_mb_mask, y_mb, y_mb_mask = next(train_itr)
train_itr.reset()
prev_h1, prev_h2, prev_h3 = [np_zeros((minibatch_size, n_hid))
for i in range(3)]
predict_function = checkpoint_dict["predict_function"]
sample_function = checkpoint_dict["sample_function"]
if args.sample_length is None:
raise ValueError("NYI - use -sl or --sample_length ")
else:
fixed_steps = args.sample_length
completed = []
init_x = np.zeros_like(X_mb[0]) + int(n_bins // 2)
for i in range(fixed_steps):
if i % 100 == 0:
print("Sampling step %i" % i)
# remove second init_x later
required=False)
args = parser.parse_args()
if args.sample is not None:
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
checkpoint_file = args.sample
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
X_mb, X_mb_mask = next(train_itr)
train_itr.reset()
prev_h1, prev_h2, prev_h3 = [np_zeros((minibatch_size, n_hid))
for i in range(3)]
predict_function = checkpoint_dict["predict_function"]
sample_function = checkpoint_dict["sample_function"]
if args.temperature is None:
args.temperature = 1.
if args.sample_length is None:
raise ValueError("NYI - use -sl or --sample_length ")
else:
fixed_steps = args.sample_length
temperature = args.temperature
completed = []
# 0 is in the middle
# CANNOT BE 1 timestep - will get floating point exception!
required=False)
args = parser.parse_args()
if args.sample is not None:
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
checkpoint_file = args.sample
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
X_mb, X_mb_mask, c_mb, c_mb_mask = next(train_itr)
train_itr.reset()
prev_h1, prev_h2, prev_h3 = [np_zeros((minibatch_size, n_hid))
for i in range(3)]
prev_kappa = np_zeros((minibatch_size, n_att_size))
prev_w = np_zeros((minibatch_size, n_chars))
predict_function = checkpoint_dict["predict_function"]
sample_function = checkpoint_dict["sample_function"]
if args.temperature is None:
args.temperature = 1.
if args.sample_length is None:
raise ValueError("NYI - use -sl or --sample_length ")
else:
sample_string = 'apple'
print("Sampling using sample string %s" % sample_string)
oh = speech_ds.dense_to_one_hot(
args = parser.parse_args()
if args.sample is not None:
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
checkpoint_file = args.sample
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
X_mb, X_mb_mask = next(train_itr)
train_itr.reset()
prev_h1, prev_h2, prev_h3 = [
np_zeros((minibatch_size, n_hid)) for i in range(3)
]
predict_function = checkpoint_dict["predict_function"]
sample_function = checkpoint_dict["sample_function"]
if args.temperature is None:
args.temperature = 1.
if args.sample_length is None:
raise ValueError("NYI - use -sl or --sample_length ")
else:
fixed_steps = args.sample_length
temperature = args.temperature
completed = []
# 0 is in the middle
# CANNOT BE 1 timestep - will get floating point exception!
else:
checkpoint_file = args.plot
if not os.path.exists(checkpoint_file):
raise ValueError("Checkpoint file path %s" % checkpoint_file,
" does not exist!")
print(checkpoint_file)
checkpoint_dict = load_checkpoint(checkpoint_file)
train_costs = checkpoint_dict["train_costs"]
valid_costs = checkpoint_dict["valid_costs"]
plt.plot(train_costs)
plt.plot(valid_costs)
plt.savefig("costs.png")
X_mb, X_mb_mask, c_mb, c_mb_mask = next(valid_itr)
valid_itr.reset()
prev_h1, prev_h2, prev_h3 = [np_zeros((minibatch_size, n_hid))
for i in range(3)]
prev_kappa = np_zeros((minibatch_size, att_size))
prev_w = np_zeros((minibatch_size, n_chars))
if args.sample is not None:
predict_function = checkpoint_dict["predict_function"]
attention_function = checkpoint_dict["attention_function"]
sample_function = checkpoint_dict["sample_function"]
if args.write is not None:
sample_string = args.write
print("Sampling using sample string %s" % sample_string)
oh = dense_to_one_hot(
np.array([vocabulary[c] for c in sample_string]),
vocabulary_size)
c_mb = np.zeros(
(len(oh), minibatch_size, oh.shape[-1])).astype(c_mb.dtype)
