Skip to content

Fix for #153 -- Stripping of the prefix wasn't occurring #154

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
InconsolableCellist wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fix for #153 -- Stripping of the prefix wasn't occurring #154

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5e17cc3
Fixing #153, and try catch
Jan 3, 2020
c4d23ba
Removing unrelated code for the #153 fix
Jan 3, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 25 additions & 8 deletions gpt_2_simple/gpt_2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -303,7 +303,7 @@ def generate_samples():
with open(
os.path.join(SAMPLE_DIR, run_name,
'samples-{}').format(counter), 'w') as fp:
fp.write('\n'.join(all_text))
fp.write('\n'.join(all_text))

def sample_batch():
return [data_sampler.sample(1024) for _ in range(batch_size)]
Expand Down Expand Up @@ -473,25 +473,42 @@ def generate(sess,
for i in range(batch_size):
generated += 1
gen_text = enc.decode(out[i])
# process the text to strip out the prefix and/or end at the truncate text
if prefix:
gen_text = enc.decode(context_tokens[:1]) + gen_text
if truncate:
truncate_esc = re.escape(truncate)
if prefix and not include_prefix:
prefix_esc = re.escape(prefix)
pattern = '(?:{})(.*?)(?:{})'.format(prefix_esc,
truncate_esc)
pattern = '(?:{})(.*?)(?:{})'.format(prefix_esc, truncate_esc)
else:
pattern = '(.*?)(?:{})'.format(truncate_esc)

trunc_text = re.search(pattern, gen_text, re.S)
if trunc_text:
gen_text = trunc_text.group(1)
gen_text = gen_text.lstrip('\n')
if destination_path:
f.write("{}\n{}".format(gen_text, sample_delim))
if not return_as_list and not destination_path:
print("{}\n{}".format(gen_text, sample_delim), end='')
# the generated text sometimes doesn't include the truncate text, but we can try again to just strip out the prefix (if it exists), leaving only the new gen_text
elif not trunc_text and prefix:
pattern = '(?:{})(.*)'.format(prefix_esc)
trunc_text = re.search(pattern, gen_text, re.S)
if trunc_text:
gen_text = trunc_text.group(1)

# truncate is not set, but we should still strip the prefix, if set and requested
else:
if prefix and not include_prefix:
prefix_esc = re.escape(prefix)
pattern = '(?:{})(.*)'.format(prefix_esc)
trunc_text = re.search(pattern, gen_text, re.S)
if trunc_text:
gen_text = trunc_text.group(1)
try:
if destination_path:
f.write("{}\n{}".format(gen_text, sample_delim))
if not return_as_list and not destination_path:
print("{}\n{}".format(gen_text, sample_delim), end='')
except Exception as e:
pass
gen_texts.append(gen_text)

if destination_path:
Expand Down