import sys
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
from framework import lib
from framework import model_neural_trad
from framework import evaluation
from framework import data
from framework import config
########################################################################################
lib.create_dir(config.results_dir + '/imageimportance')
architecture = 'langmod'
lib.create_dir(config.results_dir + '/imageimportance/' + architecture)
if not lib.file_exists(config.results_dir + '/imageimportance/' +
architecture + '/results_langmod.txt'):
with open(config.results_dir + '/imageimportance/' + architecture +
'/results_langmod.txt',
'w',
encoding='utf-8') as f:
print('dataset',
'run',
'sent_len',
'token_index',
'gradient_wrt_prefix_next',
'gradient_wrt_prefix_max',
'gradient_wrt_prevtoken_next',
'gradient_wrt_prevtoken_max',
'gradient_wrt_firsttoken_next',
'gradient_wrt_firsttoken_max',
'gradient_wrt_multimodalvec_next',
capgen_test = data.load_datasources('mscoco')['test'].shuffle(0).take(
datasources['test'].num_groups, whole_groups=True
) #MSCOCO test is never used in langmodtrans experiments so we can validate on it
del datasources
lib.create_dir(config.hyperpar_dir + '/langmodtrans')
for corpus in corpora:
lib.create_dir(config.hyperpar_dir + '/langmodtrans/' + corpus)
print('=' * 100)
print(lib.formatted_clock())
print(corpus, '1 (language model)')
print()
if lib.file_exists(config.hyperpar_dir + '/langmodtrans/' + corpus +
'/2_best.txt'):
print('Found ready')
print()
continue
print('#',
'init_method',
'max_init_weight',
'embed_size',
'rnn_size',
'post_image_size',
'pre_output_size',
'post_image_activation',
'rnn_type',
'optimizer',
'learning_rate',
########################################################################################
if len(sys.argv) == 1:
corpora = 'lm1b,mscoco,flickr8k'.split(',')
else:
corpora = sys.argv[1].split(',')
datasources = data.load_datasources(config.langmodtrans_capgen_dataset)
capgen_size = datasources['train'].size
capgen_test = datasources['test']
del datasources
lib.create_dir(config.results_dir + '/langmodtrans')
for corpus in corpora:
lib.create_dir(config.results_dir + '/langmodtrans/' + corpus)
if not lib.file_exists(config.results_dir + '/langmodtrans/' + corpus +
'/results.txt'):
with open(config.results_dir + '/langmodtrans/' + corpus +
'/results.txt',
'w',
encoding='utf-8') as f:
print('corpus',
'frozen_prefix',
'corpus_size_factor_exponent',
'run',
'corpus_size',
'langmod_vocab_size',
'langmod_num_params',
'langmod_mean_prob',
'langmod_median_prob',
'langmod_geomean_prob',
'langmod_mean_pplx',
dataset.compile_sents()
test_images = dataset.test.get_images()
test_sents = dataset.test.get_text_sent_groups()
lib.create_dir(config.hyperpar_dir + '/whereimage')
for architecture in architectures:
lib.create_dir(config.hyperpar_dir + '/whereimage/' + architecture)
print('=' * 100)
print(lib.formatted_clock())
print(architecture)
print()
if lib.file_exists(config.hyperpar_dir + '/whereimage/' + architecture +
'/best.txt'):
print('Found ready')
print()
continue
print('#',
'init_method',
'max_init_weight',
'embed_size',
'rnn_size',
'post_image_size',
'pre_output_size',
'post_image_activation',
'rnn_type',
'optimizer',
'learning_rate',
########################################################################################
if len(sys.argv) == 1:
corpora = 'flickr8k,mscoco,lm1b'.split(',')
else:
corpora = sys.argv[1].split(',')
datasources = data.load_datasources(config.langmodtrans_capgen_dataset)
capgen_size = datasources['train'].size
capgen_test = datasources['test']
del datasources
lib.create_dir(config.results_dir+'/partialtraining')
for corpus in corpora:
lib.create_dir(config.results_dir+'/partialtraining/'+corpus)
if not lib.file_exists(config.results_dir+'/partialtraining/'+corpus+'/results1_earlystop.txt'):
with open(config.results_dir+'/partialtraining/'+corpus+'/results1_earlystop.txt', 'w', encoding='utf-8') as f:
print(
'corpus',
'frozen_prefix',
'max_epochs',
'run',
'corpus_size',
'langmod_vocab_size',
'langmod_num_params',
'langmod_mean_prob',
'langmod_median_prob',
'langmod_geomean_prob',
'langmod_mean_pplx',
'langmod_median_pplx',
'langmod_geomean_pplx',
print(' | ', end='\t')
print(round(train_logpplx, 3), round(val_logpplx, 3), lib.format_duration(self.epoch_timer.get_duration()), sep='\t')
self.training_prog = None
########################################################################################
datasources = data.load_datasources(config.langmodtrans_capgen_dataset)
capgen_size = datasources['train'].size
capgen_test = datasources['test']
del datasources
lib.create_dir(config.results_dir+'/randomrnn')
corpus = 'flickr8k'
lib.create_dir(config.results_dir+'/randomrnn/'+corpus)
if not lib.file_exists(config.results_dir+'/randomrnn/'+corpus+'/results.txt'):
with open(config.results_dir+'/randomrnn/'+corpus+'/results.txt', 'w', encoding='utf-8') as f:
print(
'corpus',
'frozen_prefix',
'max_epochs',
'run',
'corpus_size',
'langmod_vocab_size',
'langmod_num_params',
'langmod_mean_prob',
'langmod_median_prob',
'langmod_geomean_prob',
'langmod_mean_pplx',
'langmod_median_pplx',
'langmod_geomean_pplx',
lib.format_duration(self.epoch_timer.get_duration()),
sep='\t')
self.training_prog = None
########################################################################################
if len(sys.argv) == 1:
architectures = 'ceiling,merge,par,pre,init,merge-ext'.split(',')
else:
architectures = sys.argv[1].split(',')
lib.create_dir(config.results_dir + '/whereimage')
for architecture in architectures:
lib.create_dir(config.results_dir + '/whereimage/' + architecture)
if not lib.file_exists(config.results_dir + '/whereimage/' + architecture +
'/results.txt'):
with open(config.results_dir + '/whereimage/' + architecture +
'/results.txt',
'w',
encoding='utf-8') as f:
print('architecture',
'dataset',
'run',
'vocab_size',
'num_params',
'mean_prob',
'median_prob',
'geomean_prob',
'mean_pplx',
'median_pplx',
'geomean_pplx',