# flickr doesnt need to be split at the root node
def iterate_data(h5_file):
for x in h5_file.root:
yield x
f_nodes = [node for node in iterate_data(data_file)]
# split the database into train test and validation sets. default settings uses the json file
# with the karpathy split
train, test, val = split_data(f_nodes, args.split_loc)
############################### Neural network setup #################################################
# network modules
img_net = img_encoder(image_config)
cap_net = text_gru_encoder(token_config)
# Adam optimiser. I found SGD to work terribly and could not find appropriate parameter settings for it.
optimizer = torch.optim.Adam(
list(img_net.parameters()) + list(cap_net.parameters()), 1)
#plateau_scheduler = lr_scheduler.ReduceLROnPlateau(optimizer, mode = 'min', factor = 0.9, patience = 100,
# threshold = 0.0001, min_lr = 1e-8, cooldown = 100)
#step_scheduler = lr_scheduler.StepLR(optimizer, 1000, gamma=0.1, last_epoch=-1)
def create_cyclic_scheduler(max_lr, min_lr, stepsize):
lr_lambda = lambda iteration: (max_lr - min_lr) * (0.5 * (np.cos(np.pi * (
1 + (3 - 1) / stepsize * iteration)) + 1)) + min_lr
cyclic_scheduler = lr_scheduler.LambdaLR(optimizer,
yield y
f_nodes = [node for node in iterate_data(data_file)]
# split the database into train test and validation sets. default settings uses the json file
# with the karpathy split
train, val = split_data_coco(f_nodes)
# set aside 5000 images as test set
test = train[-5000:]
train = train[:-5000]
#####################################################
# network modules
img_net = img_encoder(image_config)
cap_net = text_gru_encoder(char_config)
# list all the trained model parameters
models = os.listdir(args.results_loc)
caption_models = [x for x in models if 'caption' in x]
img_models = [x for x in models if 'image' in x]
# create a trainer with just the evaluator for the purpose of testing a pretrained model
trainer = flickr_trainer(img_net, cap_net, args.visual, args.cap)
trainer.set_raw_text_batcher()
# optionally use cuda
if cuda:
trainer.set_cuda()
trainer.set_evaluator([1, 5, 10])
for img, cap in zip(img_models, caption_models):
'gru': {
'input_size': 20,
'hidden_size': 1024,
'num_layers': 1,
'batch_first': True,
'bidirectional': True,
'dropout': 0
},
'att': {
'in_size': 2048,
'hidden_size': 128,
'heads': 1
}
}
# create encoder
encoder = text_gru_encoder(text_config)
for p in encoder.parameters():
p.requires_grad = False
encoder.cuda()
# load pretrained model
encoder_state = torch.load(PATH_TO_ENC)
encoder.load_state_dict(encoder_state)
# Set params for SentEval
params_senteval = {'task_path': PATH_TO_DATA, 'usepytorch': True, 'kfold': 5}
params_senteval['classifier'] = {
'nhid': 0,
'optim': 'rmsprop',
'batch_size': 128,
'tenacity': 3,
'epoch_size': 10
