def run_epoch(session,
model,
eval_op=None,
verbose=False,
is_training=True,
save_file=None):
"""Runs the model on the given data."""
start_time = time.time()
costs = 0.0
iters = 0
acc = 0.0
state_fw, state_bw = session.run(
[model.initial_state_fw, model.initial_state_bw])
fetches = {
"cost": model.cost,
"final_state_fw": model.final_state_fw,
"final_state_bw": model.final_state_bw,
"accuracy": model.accuracy,
"logits": model.logits,
#"targets":model.targets,
#"length":model.length
#"loss_masked": model.loss_masked
}
if eval_op is not None:
fetches["eval_op"] = eval_op
for step in range(model.input.epoch_size):
feed_dict = {}
for i, (c, h) in enumerate(model.initial_state_fw):
feed_dict[c] = state_fw[i].c
feed_dict[h] = state_fw[i].h
for i, (c, h) in enumerate(model.initial_state_bw):
feed_dict[c] = state_bw[i].c
feed_dict[h] = state_bw[i].h
vals = session.run(fetches, feed_dict)
if is_training == False:
if save_file is not None:
result = vals["logits"]
#print(result)
#for word in (result):
# save_file.write(str(word)+" ")
#save_file.write("\n")
predict_result.genPredict(array(result, dtype=int32),
test_path=FLAGS.test_path)
cost = vals["cost"]
state_fw = vals["final_state_fw"]
state_bw = vals["final_state_bw"]
costs += cost
iters += model.input.num_steps
acc += vals["accuracy"]
if verbose and step % (model.input.epoch_size // 10) == 10:
print("%.3f Loss: %.3f Speed: %.0f wps Acc: %.3f" %
(step * 1.0 / model.input.epoch_size, np.exp(costs / iters),
iters * model.input.batch_size * max(1, FLAGS.num_gpus) /
(time.time() - start_time), acc /
(iters // model.input.num_steps)))
return np.exp(costs / iters), acc / (iters // model.input.num_steps)
def run_epoch(session,
model,
eval_op=None,
verbose=False,
is_training=True,
save_file=None):
if is_training == False:
result = session.run(model.logits)
r1 = []
for word in (result[0]):
for backup in word:
r1.append(backup)
#save_file.write(str(backup)+" ")
#save_file.write("\n")
predict_result.genPredict(array(r1, dtype=float32),
test_path=FLAGS.test_path)
#np.savetxt(save_file,reshape(result,[-1,9175]),fmt="%.18e")
return
"""Runs the model on the given data."""
start_time = time.time()
costs = 0.0
iters = 0
state = session.run(model.initial_state)
fetches = {
"cost": model.cost,
"final_state": model.final_state,
}
if eval_op is not None:
fetches["eval_op"] = eval_op
for step in range(model.input.epoch_size):
feed_dict = {}
for i, (c, h) in enumerate(model.initial_state):
feed_dict[c] = state[i].c
feed_dict[h] = state[i].h
vals = session.run(fetches, feed_dict)
cost = vals["cost"]
state = vals["final_state"]
costs += cost
iters += model.input.num_steps
if verbose and step % (model.input.epoch_size // 10) == 10:
print("%.3f perplexity: %.3f speed: %.0f wps" %
(step * 1.0 / model.input.epoch_size, np.exp(costs / iters),
iters * model.input.batch_size * max(1, FLAGS.num_gpus) /
(time.time() - start_time)))
return np.exp(costs / iters)