Something went wrong on our end
constants_crunchy.py 9.66 KiB
import os
import pdb
def mkdir_if_not_exists(dir_name):
if not os.path.exists(dir_name):
os.mkdir(dir_name)
experiment_name = 'ans_through_obj_atr_no_rel_bin_discon'
##########################################################################
# Machine Specific Paths #
##########################################################################
# Global output directory (all subexperiments will be saved here)
global_output_dir = '/home/tanmay/Code/GenVQA/Exp_Results/models_cvpr'
global_experiment_dir = os.path.join(
global_output_dir,
experiment_name)
tb_log_dir = os.path.join(
global_experiment_dir,
'tensorboard_logdir')
mkdir_if_not_exists(global_output_dir)
mkdir_if_not_exists(global_experiment_dir)
mkdir_if_not_exists(tb_log_dir)
# Genome Parent Directory
data_absolute_path = '/home/ssd/VisualGenome'
# Pretrained resnet ckpt
resnet_ckpt = '/home/tanmay/Downloads/pretrained_networks/' + \
'Resnet/tensorflow-resnet-pretrained-20160509/' + \
'ResNet-L50.ckpt'
# Pretrained word vectors
word2vec_binary = '/home/tanmay/Code/word2vec/word2vec-api-master/' + \
'GoogleNews-vectors-negative300.bin'
# VQA parent directory
vqa_basedir = '/home/ssd/VQA/'
# Pretrained obj atr model to be restored
pretrained_model = '/home/tanmay/Code/GenVQA/Exp_Results/VQA/' + \
'object_attribute_classifier_wordvec_xform/' + \
'object_attribute_classifiers/model-102000'
##########################################################################
# Model Parameters #
##########################################################################
# height and width to which images are resized before feeding into networks
image_size = (224, 224)
# Token to be used if object or attribute variable is unknown
unknown_token = 'UNK'
##########################################################################
# Labels and Word2Vec Parameters #
##########################################################################
num_object_labels = 1000
num_attribute_labels = 1000
word_vector_size = 300
resnet_feat_dim = 2048
# Numpy matrix storing vocabulary word vectors
pretrained_vocab_word_vectors_npy = os.path.join(
data_absolute_path,
'restructured/pretrained_vocab_word_vectors.npy')
##########################################################################
# Genome Parameters #
##########################################################################
# Genome paths
image_dir = os.path.join(data_absolute_path, 'cropped_regions_large')
genome_resnet_feat_dir = os.path.join(
data_absolute_path,
'cropped_regions_large_resnet_features')
object_labels_json = os.path.join(
data_absolute_path,
'restructured/object_labels.json')
attribute_labels_json = os.path.join(
data_absolute_path,
'restructured/attribute_labels.json')
regions_json = os.path.join(
data_absolute_path,
'restructured/region_with_hypernym_labels.json')
eval_regions_json = os.path.join(
data_absolute_path,
'restructured/region_with_labels.json')
mean_image_filename = os.path.join(
data_absolute_path,
'restructured/mean_image.jpg')
vocab_json = os.path.join(
data_absolute_path,
'restructured/vocab_subset.json')
genome_train_region_ids = os.path.join(
data_absolute_path,
'restructured/train_region_ids_simple.json')
genome_val_region_ids = os.path.join(
data_absolute_path,
'restructured/val_region_ids_simple.json')
genome_test_region_ids = os.path.join(
data_absolute_path,
'restructured/test_region_ids_simple.json')
##########################################################################
# Genome Training/Fine-Tuning Parameters #
##########################################################################
# Logging parameters
region_log_every_n_iter = 500
region_output_dir = os.path.join(
global_experiment_dir,
'object_attribute_classifiers')
mkdir_if_not_exists(region_output_dir)
region_model = os.path.join(
region_output_dir,
'model')
# Object Attribute Classifier Training Params
region_batch_size = 200
region_num_epochs = 20
region_queue_size = 400
region_regularization_coeff = 1e-5
region_lr = 1e-3
# Object Attribute Finetuning Params
region_fine_tune_from_iter = 50500
region_fine_tune_from = region_model + '-' + str(region_fine_tune_from_iter)
##########################################################################
# Genome Evaluation Parameters #
##########################################################################
# Object Attribute Model Selection
region_start_model = 8000
region_step_size = 8000
region_model_accuracies_txt = os.path.join(
region_output_dir,
'model_accuracies.txt')
# Object Attribute Classifier Evaluation Params
region_eval_on = 'test' # One of {'test','train_held_out','train_subset'}
region_model_to_eval = region_model + '-' + '1000'
# Path to results
visualize_object_predictions = True
# Path to results
region_pred_vis_dirname = os.path.join(
region_output_dir,
'region_pred_vis_'+region_eval_on)
mkdir_if_not_exists(region_pred_vis_dirname)
region_attribute_scores_dirname = os.path.join(
region_output_dir,
'attribute_scores')
mkdir_if_not_exists(region_attribute_scores_dirname)
region_object_scores_dirname = os.path.join(
region_output_dir,
'object_scores')
mkdir_if_not_exists(region_object_scores_dirname)
##########################################################################
# VQA Parameters #
##########################################################################
# Answer prediction
num_region_proposals = 100
num_mcq_candidates = 18
num_negative_answers = num_mcq_candidates - 1
# VQA data paths
vqa_train_image_dir = os.path.join(
vqa_basedir,
'train2014_cropped_large')
vqa_train_resnet_feat_dir = os.path.join(
vqa_basedir,
'train2014_cropped_large_resnet_features')
vqa_train_anno = os.path.join(
vqa_basedir,
'mscoco_train2014_annotations_with_parsed_questions.json')
vqa_train_subset_qids = os.path.join(
vqa_basedir,
'train_subset_qids.json')
vqa_train_held_out_qids = os.path.join(
vqa_basedir,
'train_held_out_qids.json')
vqa_val_image_dir = os.path.join(
vqa_basedir,
'val2014_cropped_large')
vqa_val_resnet_feat_dir = os.path.join(
vqa_basedir,
'val2014_cropped_large_resnet_features')
vqa_val_anno = os.path.join(
vqa_basedir,
'mscoco_val2014_annotations_with_parsed_questions.json')
vqa_val_qids = os.path.join(
vqa_basedir,
'val_qids.json')
vqa_test_resnet_feat_dir = os.path.join(
vqa_basedir,
'test2015_cropped_large_resnet_features')
vqa_test_anno = os.path.join(
vqa_basedir,
'mscoco_test2015_annotations_with_parsed_questions.json')
vqa_test_qids = os.path.join(
vqa_basedir,
'test_qids.json')
vqa_testdev_anno = os.path.join(
vqa_basedir,
'mscoco_test-dev2015_annotations_with_parsed_questions.json')
vqa_testdev_qids = os.path.join(
vqa_basedir,
'test-dev_qids.json')
vqa_answer_vocab_json = os.path.join(
vqa_basedir,
'answer_vocab.json')
# Dataset statistics
# num_train_questions = 248349
# num_train_held_out_questions = 12500
# num_train_subset_questions = num_train_questions - num_train_held_out_questions
# num_val_questions = 121512
##########################################################################
# VQA Training/Finetuning Parameters #
##########################################################################
# Logging parameters
answer_log_every_n_iter = 500
answer_output_dir = os.path.join(
global_experiment_dir,
'answer_classifiers')
mkdir_if_not_exists(answer_output_dir)
answer_model = os.path.join(
answer_output_dir,
'model')
# Answer classifier training params
answer_train_from_scratch = True
answer_batch_size = 50
answer_num_epochs = 20
answer_queue_size = 500
answer_regularization_coeff = 1e-5
answer_lr = 1e-3
answer_obj_atr_loss_wt = 0.1
answer_ans_loss_wt = 1.0
answer_mil_loss_wt = 0
# Answer classifier additional joint training params
num_regions_with_labels = 100
# Answer fine tune params
answer_fine_tune_from_iter = 500
answer_fine_tune_from = answer_model + '-' + str(answer_fine_tune_from_iter)
##########################################################################
# VQA Evaluation Parameters #
##########################################################################
# Select best model
models_dir = answer_output_dir
start_model = 20000
step_size = 4000
model_accuracies_txt = os.path.join(
answer_output_dir,
'model_accuracies.txt')
# Answer eval params
answer_eval_on = 'testdev'
answer_model_to_eval = answer_model + '-43000'
vqa_results_dir = os.path.join(
answer_output_dir,
'Results')
mkdir_if_not_exists(vqa_results_dir)
answer_eval_data_json = os.path.join(
vqa_results_dir,
'eval_' + answer_eval_on + '_data.json')
answer_eval_results_json = os.path.join(
vqa_results_dir,
'eval_' + answer_eval_on + '_results.json')
# Fine Grained Evaluation File paths
raw_vqa_val_ques_json = os.path.join(
vqa_basedir,
'MultipleChoice_mscoco_val2014_questions.json')
raw_vqa_val_anno_json = os.path.join(
vqa_basedir,
'mscoco_val2014_annotations.json')
raw_vqa_test_ques_json = os.path.join(
vqa_basedir,
'MultipleChoice_mscoco_test2015_questions.json')
raw_vqa_val_anno_json = os.path.join(
vqa_basedir,
'mscoco_test2015_annotations.json')