def _EndOfEpochTestSample(
self, corpus, sampler: samplers.Sampler, step: int, epoch_num: int
):
"""Run sampler"""
import tensorflow as tf
atomizer = corpus.atomizer
sampler.Specialize(atomizer)
sampler.batch_size = 1
seed = 0
self.InitSampling(sampler, seed)
self.InitSampleBatch(sampler)
samples, stats = [], []
for i in range(FLAGS.clgen_per_epoch_test_samples):
done = np.zeros(1, dtype=np.bool)
while not done[0]:
start_time = time.time()
sample_in_progress = sampler.tokenized_start_text.copy()
indices = self.SampleNextIndices(sampler, done)
# Iterate over all samples in batch to determine whether they're
# done.
for index in indices[0]:
sample_in_progress.append(atomizer.decoder[index])
if not sampler.SampleIsComplete(sample_in_progress):
continue
stats.append(
(len(sample_in_progress), int((time.time() - start_time) * 1000))
)
sample = "".join(sample_in_progress)
samples.append(sample)
app.Log(1, "End-of-epoch sample %d:\n%s", i + 1, sample)
done[0] = True
break
# Write samples to file.
with self.dashboard_db.Session(commit=True) as dbs:
dbs.add_all(
[
dashboard_db.TrainingSample(
model_id=self.dashboard_model_id,
epoch=epoch_num,
step=step,
sample=sample,
token_count=stats[0],
sample_time=stats[1],
)
for sample, stats in zip(samples, stats)
]
)
samples_as_markdown = [
self.FormatCodeAsMarkdown(sample) for sample in samples
]
samples_tensor = tf.convert_to_tensor(samples_as_markdown, dtype=tf.string)
summary_op = tf.summary.text("samples", samples_tensor)
summary = self.inference_sess.run(summary_op)
self.summary_writer.add_summary(summary, step)
def _EndOfEpochTestSample(self, corpus, sampler: samplers.Sampler,
step: int):
"""Run sampler"""
import tensorflow as tf
atomizer = corpus.atomizer
sampler.Specialize(atomizer)
sampler.batch_size = 1
seed = 0
self.InitSampling(sampler, seed)
self.InitSampleBatch(sampler)
samples = []
for i in range(12):
done = np.zeros(1, dtype=np.bool)
while not done[0]:
sample_in_progress = sampler.tokenized_start_text.copy()
indices = self.SampleNextIndices(sampler, done)
# Iterate over all samples in batch to determine whether they're
# done.
for index in indices[0]:
sample_in_progress.append(atomizer.decoder[index])
if not sampler.SampleIsComplete(sample_in_progress):
continue
sample = ''.join(sample_in_progress)
samples.append(sample)
app.Log(1, 'End-of-epoch sample %d:\n%s', i + 1, sample)
done[0] = True
break
# Write samples to file.
samples_as_markdown = [
f'```\n{sample.strip()}\n```' for sample in samples
]
samples_tensor = tf.convert_to_tensor(samples_as_markdown,
dtype=tf.string)
summary_op = tf.summary.text('samples', samples_tensor)
summary = self.inference_sess.run(summary_op)
self.summary_writer.add_summary(summary, step)