Skip to content

[WIP] Attempt to pickle model #81

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
shuttle1987 wants to merge 2 commits into
base: master
Choose a base branch
from
Open

[WIP] Attempt to pickle model #81

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f743428
Attempt to pickle model
shuttle1987 Aug 11, 2018
2cdbf98
Attempt to debug source of pickle error
shuttle1987 Aug 12, 2018
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
22 changes: 20 additions & 2 deletions persephone_api/api_endpoints/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,21 @@
from ..db_models import DBcorpus, TranscriptionModel
from ..serialization import TranscriptionModelSchema

class MyPickler(pickle._Pickler):
def save(self, obj):
print('pickling object {0} of type {1}'.format(obj, type(obj)))
try:
pickle._Pickler.save(self, obj)
except:
import pdb; pdb.set_trace()
raise

# attempting workaround to get TF to pickle properly:
import tensorflow as tf
setattr(tf.contrib.rnn.GRUCell, '__deepcopy__', lambda self, _: self)
setattr(tf.contrib.rnn.BasicLSTMCell, '__deepcopy__', lambda self, _: self)
setattr(tf.contrib.rnn.MultiRNNCell, '__deepcopy__', lambda self, _: self)

def create_RNN_CTC_model(model: TranscriptionModel, corpus_storage_path: Path,
models_storage_path: Path):
"""Create a persephone RNN CTC model
Expand All @@ -33,14 +48,18 @@ def create_RNN_CTC_model(model: TranscriptionModel, corpus_storage_path: Path,
corpus = pickle.load(pickle_file)

corpus_reader = CorpusReader(corpus)
model = rnn_ctc.Model(
persephone_model = rnn_ctc.Model(
exp_dir,
corpus_reader,
num_layers=model.num_layers,
hidden_size=model.hidden_size,
beam_width=model.beam_width,
decoding_merge_repeated=model.decoding_merge_repeated
)
model_pickle_path = model_path / "model.p"
with model_pickle_path.open('wb') as pickle_file:
p = MyPickler(pickle_file, protocol=4)
p.dump(persephone_model)
# TODO: pickle model at this point?

def search():
Expand Down Expand Up @@ -74,7 +93,6 @@ def post(modelInfo):

model_uuid = uuid.uuid1()

import pdb; pdb.set_trace()
current_model = TranscriptionModel(
name=modelInfo['name'],
corpus=current_corpus,
Expand Down