params.scope_name or "model",
reuse=tf.AUTO_REUSE,
dtype=tf.as_dtype(dtype.floatx()),
custom_getter=dtype.float32_variable_storage_getter):
state = encoder(source, params)
state["decoder"] = {"state": state["decoder_initializer"]}
return state
def decoding_fn(target, state, time):
with tf.variable_scope(
params.scope_name or "model",
reuse=tf.AUTO_REUSE,
dtype=tf.as_dtype(dtype.floatx()),
custom_getter=dtype.float32_variable_storage_getter):
if params.search_mode == "cache":
step_loss, step_logits, step_state, _ = decoder(
target, state, params)
else:
estate = encoder(state, params)
estate['dev_decode'] = True
_, step_logits, _, _ = decoder(target, estate, params)
step_state = state
return step_logits, step_state
return encoding_fn, decoding_fn
# register the model, with a unique name
model.model_register("rnnsearch_deepatt", train_fn, score_fn, infer_fn)
dtype=tf.as_dtype(dtype.floatx()),
custom_getter=dtype.float32_variable_storage_getter):
state = encoder(source, params)
state["decoder"] = {"state": state["decoder_initializer"]}
return state
def decoding_fn(target, state, time):
with tf.variable_scope(
params.scope_name or "model",
reuse=tf.AUTO_REUSE,
dtype=tf.as_dtype(dtype.floatx()),
custom_getter=dtype.float32_variable_storage_getter):
if params.search_mode == "cache":
state['time'] = time
step_loss, step_logits, step_state, _ = decoder(
target, state, params)
del state['time']
else:
estate = encoder(state, params)
estate['dev_decode'] = True
_, step_logits, _, _ = decoder(target, estate, params)
step_state = state
return step_logits, step_state
return encoding_fn, decoding_fn
# register the model, with a unique name
model.model_register("transformer_aan", train_fn, score_fn, infer_fn)
params.scope_name or "model",
reuse=tf.AUTO_REUSE,
dtype=tf.as_dtype(dtype.floatx()),
custom_getter=dtype.float32_variable_storage_getter):
state = encoder(source, params)
state["decoder"] = {"state": state["decoder_initializer"]}
return state
def decoding_fn(target, state, time):
with tf.variable_scope(
params.scope_name or "model",
reuse=tf.AUTO_REUSE,
dtype=tf.as_dtype(dtype.floatx()),
custom_getter=dtype.float32_variable_storage_getter):
if params.search_mode == "cache":
step_loss, step_logits, step_state, _ = decoder(
target, state, params)
else:
estate = encoder(state, params)
estate['dev_decode'] = True
_, step_logits, _, _ = decoder(target, estate, params)
step_state = state
return step_logits, step_state
return encoding_fn, decoding_fn
# register the model, with a unique name
model.model_register("deepnmt", train_fn, score_fn, infer_fn)
