def load_eval_data(max_num=0):
imdb_file = cfg.IMDB_FILE % cfg.TEST.SPLIT_REF
data_reader = DataReader(
imdb_file, shuffle=False, max_num=max_num,
batch_size=cfg.TEST.BATCH_SIZE,
vocab_question_file=cfg.VOCAB_QUESTION_FILE,
T_encoder=cfg.T_ENCODER,
vocab_answer_file=cfg.VOCAB_ANSWER_FILE,
load_spatial_feature=True,
spatial_feature_dir=cfg.SPATIAL_FEATURE_DIR,
add_pos_enc=cfg.ADD_POS_ENC, img_H=cfg.IMG_H, img_W=cfg.IMG_W,
pos_enc_dim=cfg.PE_DIM, pos_enc_scale=cfg.PE_SCALE)
num_vocab = data_reader.batch_loader.vocab_dict.num_vocab
num_choices = data_reader.batch_loader.answer_dict.num_vocab
return data_reader, num_vocab, num_choices
def load_train_data(max_num=0):
load_train_time = time.time()
imdb_file = cfg.IMDB_FILE % cfg.TRAIN.SPLIT_REF
data_reader = DataReader(imdb_file,
shuffle=True,
max_num=max_num,
batch_size=cfg.TRAIN.BATCH_SIZE,
vocab_question_file=cfg.VOCAB_QUESTION_FILE,
T_encoder=cfg.T_ENCODER,
vocab_answer_file=cfg.VOCAB_ANSWER_FILE,
load_spatial_feature=True,
spatial_feature_dir=cfg.SPATIAL_FEATURE_DIR,
add_pos_enc=cfg.ADD_POS_ENC,
img_H=cfg.IMG_H,
img_W=cfg.IMG_W,
pos_enc_dim=cfg.PE_DIM,
pos_enc_scale=cfg.PE_SCALE)
#print('after data reader')
num_vocab = data_reader.batch_loader.vocab_dict.num_vocab
num_choices = data_reader.batch_loader.answer_dict.num_vocab
print('load_train_time: ', time.time() - load_train_time)
return data_reader, num_vocab, num_choices
vocab_layout_file = './exp_clevr/data/vocabulary_layout.txt'
vocab_answer_file = './exp_clevr/data/answers_clevr.txt'
imdb_file_tst = './exp_clevr/data/imdb/imdb_%s.npy' % tst_image_set
save_file = './exp_clevr/results/%s/%s.%s.txt' % (exp_name, snapshot_name, tst_image_set)
os.makedirs(os.path.dirname(save_file), exist_ok=True)
eval_output_file = './exp_clevr/eval_outputs/%s/%s.%s.txt' % (exp_name, snapshot_name, tst_image_set)
os.makedirs(os.path.dirname(eval_output_file), exist_ok=True)
assembler = Assembler(vocab_layout_file)
data_reader_tst = DataReader(imdb_file_tst, shuffle=False, one_pass=True,
batch_size=N,
T_encoder=T_encoder,
T_decoder=T_decoder,
assembler=assembler,
vocab_question_file=vocab_question_file,
vocab_answer_file=vocab_answer_file,
prune_filter_module=prune_filter_module)
num_vocab_txt = data_reader_tst.batch_loader.vocab_dict.num_vocab
num_vocab_nmn = len(assembler.module_names)
num_choices = data_reader_tst.batch_loader.answer_dict.num_vocab
# Network inputs
input_seq_batch = tf.placeholder(tf.int32, [None, None])
seq_length_batch = tf.placeholder(tf.int32, [None])
image_feat_batch = tf.placeholder(tf.float32, [None, H_feat, W_feat, D_feat])
expr_validity_batch = tf.placeholder(tf.bool, [None])
# The model for testing
merge_cfg_from_file(args.cfg)
assert cfg.EXP_NAME == os.path.basename(args.cfg).replace('.yaml', '')
if args.opts:
merge_cfg_from_list(args.opts)
# Start session
os.environ["CUDA_VISIBLE_DEVICES"] = str(cfg.GPU_ID)
sess = tf.Session(config=tf.ConfigProto(
gpu_options=tf.GPUOptions(allow_growth=cfg.GPU_MEM_GROWTH)))
# Data files
imdb_file = cfg.IMDB_FILE % cfg.TEST.SPLIT_LOC
data_reader = DataReader(
imdb_file, shuffle=False, one_pass=True, batch_size=cfg.TRAIN.BATCH_SIZE,
vocab_question_file=cfg.VOCAB_QUESTION_FILE, T_encoder=cfg.MODEL.T_ENCODER,
vocab_answer_file=cfg.VOCAB_ANSWER_FILE, load_gt_layout=True,
vocab_layout_file=cfg.VOCAB_LAYOUT_FILE, T_decoder=cfg.MODEL.T_CTRL,
img_H=cfg.MODEL.H_IMG, img_W=cfg.MODEL.W_IMG)
num_vocab = data_reader.batch_loader.vocab_dict.num_vocab
num_choices = data_reader.batch_loader.answer_dict.num_vocab
module_names = data_reader.batch_loader.layout_dict.word_list
# Inputs and model
input_seq_batch = tf.placeholder(tf.int32, [None, None])
seq_length_batch = tf.placeholder(tf.int32, [None])
image_feat_batch = tf.placeholder(
tf.float32, [None, cfg.MODEL.H_FEAT, cfg.MODEL.W_FEAT, cfg.MODEL.FEAT_DIM])
model = Model(
input_seq_batch, seq_length_batch, image_feat_batch, num_vocab=num_vocab,
num_choices=num_choices, module_names=module_names, is_training=False)
# Load config
cfg = build_cfg_from_argparse()
# Start session
os.environ["CUDA_VISIBLE_DEVICES"] = str(cfg.GPU_ID)
sess = tf.Session(config=tf.ConfigProto(gpu_options=tf.GPUOptions(
allow_growth=cfg.GPU_MEM_GROWTH)))
# Data files
imdb_file_vqa = cfg.IMDB_FILE % cfg.TRAIN.SPLIT_VQA
imdb_file_loc = cfg.IMDB_FILE % cfg.TRAIN.SPLIT_LOC
data_reader_vqa = DataReader(imdb_file_vqa,
shuffle=True,
one_pass=False,
batch_size=cfg.TRAIN.BATCH_SIZE,
vocab_question_file=cfg.VOCAB_QUESTION_FILE,
T_encoder=cfg.MODEL.T_ENCODER,
vocab_answer_file=cfg.VOCAB_ANSWER_FILE,
load_gt_layout=True,
vocab_layout_file=cfg.VOCAB_LAYOUT_FILE,
T_decoder=cfg.MODEL.T_CTRL)
data_reader_loc = DataReader(imdb_file_loc,
shuffle=True,
one_pass=False,
batch_size=cfg.TRAIN.BATCH_SIZE,
vocab_question_file=cfg.VOCAB_QUESTION_FILE,
T_encoder=cfg.MODEL.T_ENCODER,
vocab_answer_file=cfg.VOCAB_ANSWER_FILE,
load_gt_layout=True,
vocab_layout_file=cfg.VOCAB_LAYOUT_FILE,
T_decoder=cfg.MODEL.T_CTRL,
img_H=cfg.MODEL.H_IMG,