def test_finetune_last():
""" finetuning using 'last'.
"""
dataset_path = ROOT_PATH + '/data/SS-Youtube/raw.pickle'
nb_classes = 2
min_acc = 0.68
with open(VOCAB_PATH, 'r') as f:
vocab = json.load(f)
data = load_benchmark(dataset_path, vocab)
print('Loading model from {}.'.format(PRETRAINED_PATH))
model = torchmoji_transfer(nb_classes, PRETRAINED_PATH)
print(model)
model, acc = finetune(model,
data['texts'],
data['labels'],
nb_classes,
data['batch_size'],
method='last',
nb_epochs=1)
print("Finetune last SS-Youtube 1 epoch acc: {}".format(acc))
assert acc >= min_acc
def test_finetune_full():
""" finetuning using 'full'.
"""
DATASET_PATH = ROOT_PATH + '/data/SS-Youtube/raw.pickle'
nb_classes = 2
# Keras and pyTorch implementation of the Adam optimizer are slightly different and change a bit the results
# We reduce the min accuracy needed here to pass the test
# See e.g. https://discuss.pytorch.org/t/suboptimal-convergence-when-compared-with-tensorflow-model/5099/11
min_acc = 0.68
with open(VOCAB_PATH, 'r') as f:
vocab = json.load(f)
data = load_benchmark(DATASET_PATH, vocab, extend_with=10000)
print('Loading pyTorch model from {}.'.format(PRETRAINED_PATH))
model = torchmoji_transfer(nb_classes,
PRETRAINED_PATH,
extend_embedding=data['added'])
print(model)
model, acc = finetune(model,
data['texts'],
data['labels'],
nb_classes,
data['batch_size'],
method='full',
nb_epochs=1)
print("Finetune full SS-Youtube 1 epoch acc: {}".format(acc))
assert acc >= min_acc
def test_finetune_last():
""" finetuning using 'last'.
"""
dataset_path = ROOT_PATH + '/data/SS-Youtube/raw.pickle'
nb_classes = 2
min_acc = 0.68
with open(VOCAB_PATH, 'r') as f:
vocab = json.load(f)
data = load_benchmark(dataset_path, vocab)
print('Loading model from {}.'.format(PRETRAINED_PATH))
model = torchmoji_transfer(nb_classes, PRETRAINED_PATH)
print(model)
model, acc = finetune(model, data['texts'], data['labels'], nb_classes,
data['batch_size'], method='last', nb_epochs=1)
print("Finetune last SS-Youtube 1 epoch acc: {}".format(acc))
assert acc >= min_acc
def test_finetune_full():
""" finetuning using 'full'.
"""
DATASET_PATH = ROOT_PATH+'/data/SS-Youtube/raw.pickle'
nb_classes = 2
# Keras and pyTorch implementation of the Adam optimizer are slightly different and change a bit the results
# We reduce the min accuracy needed here to pass the test
# See e.g. https://discuss.pytorch.org/t/suboptimal-convergence-when-compared-with-tensorflow-model/5099/11
min_acc = 0.68
with open(VOCAB_PATH, 'r') as f:
vocab = json.load(f)
data = load_benchmark(DATASET_PATH, vocab, extend_with=10000)
print('Loading pyTorch model from {}.'.format(PRETRAINED_PATH))
model = torchmoji_transfer(nb_classes, PRETRAINED_PATH, extend_embedding=data['added'])
print(model)
model, acc = finetune(model, data['texts'], data['labels'], nb_classes,
data['batch_size'], method='full', nb_epochs=1)
print("Finetune full SS-Youtube 1 epoch acc: {}".format(acc))
assert acc >= min_acc
nb_model_classes,
weight_path,
extend_embedding=data['added'])
print(model)
# Training
print('Training: {}'.format(path))
if use_f1_score:
model, result = class_avg_finetune(model, data['texts'],
data['labels'],
nb_classes, data['batch_size'],
FINETUNE_METHOD,
verbose=VERBOSE)
else:
model, result = finetune(model, data['texts'], data['labels'],
nb_classes, data['batch_size'],
FINETUNE_METHOD, metric='acc',
verbose=VERBOSE)
# Write results
if use_f1_score:
print('Overall F1 score (dset = {}): {}'.format(dset, result))
with open('{}/{}_{}_{}_results.txt'.
format(RESULTS_DIR, dset, FINETUNE_METHOD, rerun_iter),
"w") as f:
f.write("F1: {}\n".format(result))
else:
print('Test accuracy (dset = {}): {}'.format(dset, result))
with open('{}/{}_{}_{}_results.txt'.
format(RESULTS_DIR, dset, FINETUNE_METHOD, rerun_iter),
"w") as f:
f.write("Acc: {}\n".format(result))
4) Unfreeze all layers and train entire model.
"""
from __future__ import print_function
import example_helper
import json
from torchmoji.model_def import torchmoji_transfer
from torchmoji.global_variables import PRETRAINED_PATH
from torchmoji.finetuning import (
load_benchmark,
finetune)
DATASET_PATH = '../data/kaggle-insults/raw.pickle'
nb_classes = 2
with open('../model/vocabulary.json', 'r') as f:
vocab = json.load(f)
# Load dataset. Extend the existing vocabulary with up to 10000 tokens from
# the training dataset.
data = load_benchmark(DATASET_PATH, vocab, extend_with=10000)
# Set up model and finetune. Note that we have to extend the embedding layer
# with the number of tokens added to the vocabulary.
model = torchmoji_transfer(nb_classes, PRETRAINED_PATH, extend_embedding=data['added'])
print(model)
model, acc = finetune(model, data['texts'], data['labels'], nb_classes,
data['batch_size'], method='chain-thaw')
print('Acc: {}'.format(acc))
# Training
print('Training: {}'.format(path))
if use_f1_score:
model, result = class_avg_finetune(model,
data['texts'],
data['labels'],
nb_classes,
data['batch_size'],
FINETUNE_METHOD,
verbose=VERBOSE)
else:
model, result = finetune(model,
data['texts'],
data['labels'],
nb_classes,
data['batch_size'],
FINETUNE_METHOD,
metric='acc',
verbose=VERBOSE)
# Write results
if use_f1_score:
print('Overall F1 score (dset = {}): {}'.format(dset, result))
with open(
'{}/{}_{}_{}_results.txt'.format(RESULTS_DIR, dset,
FINETUNE_METHOD,
rerun_iter), "w") as f:
f.write("F1: {}\n".format(result))
else:
print('Test accuracy (dset = {}): {}'.format(dset, result))
with open(