moreo
/
kernel_authorship
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

adding patience to cmd line args

This commit is contained in:
Alejandro Moreo Fernandez 2021-02-17 12:01:13 +01:00
parent c8a0b725fc
commit 7cf29732c5
1 changed files with 22 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
src/main.py
View File

@ -59,7 +59,7 @@ def instantiate_model(A, index, pad_index, device):
channels_out=opt.chout, channels_out=opt.chout,
kernel_sizes=opt.kernelsizes), kernel_sizes=opt.kernelsizes),
ff=FFProjection(input_size=len(opt.kernelsizes) * opt.chout, ff=FFProjection(input_size=len(opt.kernelsizes) * opt.chout,
hidden_sizes=[512], hidden_sizes=[1024, 512],
output_size=opt.repr, output_size=opt.repr,
activation=nn.functional.relu, activation=nn.functional.relu,
dropout=0.5, dropout=0.5,
@ -107,10 +107,27 @@ def main(opt):
with open(f'results_feb_{opt.mode}.txt', 'wt') as foo: with open(f'results_feb_{opt.mode}.txt', 'wt') as foo:
Xtr_, Xval_, ytr_, yval_ = train_test_split(Xtr, ytr, test_size=0.1, stratify=ytr) Xtr_, Xval_, ytr_, yval_ = train_test_split(Xtr, ytr, test_size=0.1, stratify=ytr)
print('training end-to-end without self-supervision init')
cls, phi = instantiate_model(A, index, pad_index, device)
# train
val_microf1 = cls.fit(Xtr_, ytr_, Xval_, yval_,
batch_size=opt.batchsize, epochs=opt.epochs, alpha=opt.alpha, lr=opt.lr,
log=f'{opt.log}/{method}-{dataset_name}.csv',
checkpointpath=opt.checkpoint, patience=opt.patience)
# test
yte_ = cls.predict(Xte)
print('end-to-end (w/o self-supervised initialization) network prediction')
acc, macrof1, microf1 = evaluation(yte, yte_)
foo.write(f'end-to-end (w/o self-supervised initialization) '
f'network prediction: acc={acc:.3f} macrof1={macrof1:.3f} microf1={microf1:.3f}\n')
cls, phi = instantiate_model(A, index, pad_index, device)
cls.supervised_contrastive_learning(Xtr_, ytr_, Xval_, yval_, cls.supervised_contrastive_learning(Xtr_, ytr_, Xval_, yval_,
batch_size=opt.batchsize, epochs=opt.epochs, lr=opt.lr, batch_size=opt.batchsize, epochs=opt.epochs, lr=opt.lr,
log=f'{opt.log}/{method}-{dataset_name}.csv', log=f'{opt.log}/{method}-{dataset_name}.csv',
checkpointpath=opt.checkpoint) checkpointpath=opt.checkpoint, patience=opt.patience)
# svm_experiment(cls.project(Xtr), ytr, cls.project(Xte), yte, foo, 'svm-pre') # svm_experiment(cls.project(Xtr), ytr, cls.project(Xte), yte, foo, 'svm-pre')
Xtr_svm, Xte_svm = cls.project_kernel(Xtr), cls.project_kernel(Xte) Xtr_svm, Xte_svm = cls.project_kernel(Xtr), cls.project_kernel(Xte)
@ -118,7 +135,7 @@ def main(opt):
val_microf1 = cls.train_linear_classifier(Xtr_, ytr_, Xval_, yval_, val_microf1 = cls.train_linear_classifier(Xtr_, ytr_, Xval_, yval_,
batch_size=opt.batchsize, epochs=opt.epochs, lr=opt.lr, batch_size=opt.batchsize, epochs=opt.epochs, lr=opt.lr,
log=f'{opt.log}/{method}-{dataset_name}.csv', log=f'{opt.log}/{method}-{dataset_name}.csv',
checkpointpath=opt.checkpoint) checkpointpath=opt.checkpoint, patience=opt.patience)
# test # test
yte_ = cls.predict(Xte) yte_ = cls.predict(Xte)
print('sav(fix)-lin(trained) network prediction') print('sav(fix)-lin(trained) network prediction')
@ -129,8 +146,7 @@ def main(opt):
val_microf1 = cls.fit(Xtr_, ytr_, Xval_, yval_, val_microf1 = cls.fit(Xtr_, ytr_, Xval_, yval_,
batch_size=opt.batchsize, epochs=opt.epochs, alpha=opt.alpha, lr=opt.lr, batch_size=opt.batchsize, epochs=opt.epochs, alpha=opt.alpha, lr=opt.lr,
log=f'{opt.log}/{method}-{dataset_name}.csv', log=f'{opt.log}/{method}-{dataset_name}.csv',
checkpointpath=opt.checkpoint checkpointpath=opt.checkpoint, patience=opt.patience)
)
# test # test
yte_ = cls.predict(Xte) yte_ = cls.predict(Xte)
print('end-to-end-finetuning network prediction') print('end-to-end-finetuning network prediction')
@ -138,21 +154,6 @@ def main(opt):
foo.write(f'end-to-end-finetuning network prediction: ' foo.write(f'end-to-end-finetuning network prediction: '
f'acc={acc:.3f} macrof1={macrof1:.3f} microf1={microf1:.3f}\n') f'acc={acc:.3f} macrof1={macrof1:.3f} microf1={microf1:.3f}\n')
print('training end-to-end without self-supervision init')
cls, phi = instantiate_model(A, index, pad_index, device)
# train
val_microf1 = cls.fit(Xtr_, ytr_, Xval_, yval_,
batch_size=opt.batchsize, epochs=opt.epochs, alpha=opt.alpha, lr=opt.lr,
log=f'{opt.log}/{method}-{dataset_name}.csv',
checkpointpath=opt.checkpoint
)
# test
yte_ = cls.predict(Xte)
print('end-to-end (w/o self-supervised initialization) network prediction')
acc, macrof1, microf1 = evaluation(yte, yte_)
foo.write(f'end-to-end (w/o self-supervised initialization) '
f'network prediction: acc={acc:.3f} macrof1={macrof1:.3f} microf1={microf1:.3f}\n')
svm_experiment(Xtr_svm, ytr, Xte_svm, yte, foo, 'svm-kernel') svm_experiment(Xtr_svm, ytr, Xte_svm, yte, foo, 'svm-kernel')
# results = Results(opt.output) # results = Results(opt.output)
@ -206,7 +207,7 @@ def svm_experiment(Xtr, ytr, Xte, yte, foo, name):
if __name__ == '__main__': if __name__ == '__main__':
parser = argparse.ArgumentParser(description='CNN with KTA regularization') parser = argparse.ArgumentParser(description='CNN with KTA regularization')
parser.add_argument('-H', '--hidden', help='Hidden/embedding size', type=int, default=16) parser.add_argument('-H', '--hidden', help='Hidden/embedding size', type=int, default=32)
parser.add_argument('-c', '--chout', help='Channels output size', type=int, default=128) parser.add_argument('-c', '--chout', help='Channels output size', type=int, default=128)
parser.add_argument('-r', '--repr', help='Projection size (phi)', type=int, default=256) parser.add_argument('-r', '--repr', help='Projection size (phi)', type=int, default=256)
parser.add_argument('-k', '--kernelsizes', help='Size of the convolutional kernels', nargs='+', default=[6,7,8]) parser.add_argument('-k', '--kernelsizes', help='Size of the convolutional kernels', nargs='+', default=[6,7,8])