def extract(path_opts=None):
Options(path_opts)
utils.set_random_seed(Options()['misc']['seed'])
assert Options(
)['dataset']['eval_split'] is not None, 'eval_split must be set'
assert Options(
)['dataset']['train_split'] is None, 'train_split must be None'
init_logs_options_files(Options()['exp']['dir'],
Options()['exp']['resume'])
Logger().log_dict('options', Options(), should_print=True)
Logger()(os.uname())
if torch.cuda.is_available():
cudnn.benchmark = True
Logger()('Available GPUs: {}'.format(utils.available_gpu_ids()))
engine = engines.factory()
engine.dataset = datasets.factory(engine)
engine.model = models.factory(engine)
engine.view = views.factory(engine)
# init extract directory
dir_extract = os.path.join(Options()['exp']['dir'], 'extract',
Options()['dataset']['eval_split'])
os.system('mkdir -p ' + dir_extract)
path_img_embs = os.path.join(dir_extract, 'image_emdeddings.pth')
path_rcp_embs = os.path.join(dir_extract, 'recipe_emdeddings.pth')
img_embs = torch.FloatTensor(len(engine.dataset['eval']),
Options()['model.network.dim_emb'])
rcp_embs = torch.FloatTensor(len(engine.dataset['eval']),
Options()['model.network.dim_emb'])
def save_embeddings(module, input, out):
nonlocal img_embs
nonlocal rcp_embs
batch = input[0] # tuple of len=1
for j, idx in enumerate(batch['recipe']['index']):
# path_image = os.path.join(dir_image, '{}.pth'.format(idx))
# path_recipe = os.path.join(dir_recipe, '{}.pth'.format(idx))
# torch.save(out['image_embedding'][j].data.cpu(), path_image)
# torch.save(out['recipe_embedding'][j].data.cpu(), path_recipe)
img_embs[idx] = out['image_embedding'][j].data.cpu()
rcp_embs[idx] = out['recipe_embedding'][j].data.cpu()
engine.model.register_forward_hook(save_embeddings)
engine.resume()
engine.eval()
Logger()('Saving image embeddings to {} ...'.format(path_img_embs))
torch.save(img_embs, path_img_embs)
Logger()('Saving recipe embeddings to {} ...'.format(path_rcp_embs))
torch.save(rcp_embs, path_rcp_embs)
def main(path_opts=None):
# first call to Options() load the options yaml file from --path_opts command line argument if path_opts=None
Options(path_opts)
# make exp directory if resume=None
init_experiment_directory(Options()['exp']['dir'],
Options()['exp']['resume'])
# initialiaze seeds to be able to reproduce experiment on reload
utils.set_random_seed(Options()['misc']['seed'])
# display and save options as yaml file in exp dir
Logger().log_dict('options', Options(), should_print=True)
# display server name and GPU(s) id(s)
Logger()(os.uname())
if 'CUDA_VISIBLE_DEVICES' in os.environ:
Logger()('CUDA_VISIBLE_DEVICES=' + os.environ['CUDA_VISIBLE_DEVICES'])
# engine can train, eval, optimize the model
# engine can save and load the model and optimizer
engine = engines.factory()
# dataset is a dictionnary which contains all the needed datasets indexed by splits
# (example: dataset.keys() -> ['train','val'])
dataset = datasets.factory()
engine.dataset = dataset
# model includes a network, a criterion and a metric
# model can register engine hooks (begin epoch, end batch, end batch, etc.)
# (example: "calculate mAP at the end of the evaluation epoch")
model = models.factory(engine)
engine.model = model
# optimizer can register engine hooks
optimizer = optimizers.factory(model, engine)
engine.optimizer = optimizer
# load the model and optimizer from a checkpoint
if Options()['exp']['resume']:
engine.resume()
# if no training split, evaluate the model on the evaluation split
# (example: $ python main.py --dataset.train_split --dataset.eval_split test)
engine.eval()
# optimize the model on the training split for several epochs
# (example: $ python main.py --dataset.train_split train)
# if evaluation split, evaluate the model after each epochs
# (example: $ python main.py --dataset.train_split train --dataset.eval_split val)
engine.train()
def api(path_opts=None):
global engine
global img_embs
global rcp_embs
global all_embs
global all_ids
Options(path_opts)
utils.set_random_seed(Options()['misc']['seed'])
assert Options(
)['dataset']['eval_split'] is not None, 'eval_split must be set'
assert Options(
)['dataset']['train_split'] is None, 'train_split must be None'
init_logs_options_files(Options()['exp']['dir'],
Options()['exp']['resume'])
Logger().log_dict('options', Options(), should_print=True)
Logger()(os.uname())
if torch.cuda.is_available():
cudnn.benchmark = True
Logger()('Available GPUs: {}'.format(utils.available_gpu_ids()))
engine = engines.factory()
engine.dataset = datasets.factory(engine)
engine.model = models.factory(engine)
engine.model.eval()
engine.resume()
dir_extract = os.path.join(Options()['exp']['dir'], 'extract',
Options()['dataset']['eval_split'])
path_img_embs = os.path.join(dir_extract, 'image_emdeddings.pth')
path_rcp_embs = os.path.join(dir_extract, 'recipe_emdeddings.pth')
img_embs = torch.load(path_img_embs)
rcp_embs = torch.load(path_rcp_embs)
all_embs = torch.cat([img_embs, rcp_embs], dim=0)
all_ids = list(range(img_embs.shape[0])) + list(range(rcp_embs.shape[0]))
my_local_ip = '132.227.204.160' # localhost | 192.168.0.41 (hostname --ip-address)
my_local_port = 3456 # 8080 | 3456
run_simple(my_local_ip, my_local_port, application)
import bootstrap.engines as engines
import bootstrap.models as models
import bootstrap.datasets as datasets
from bootstrap.lib.logger import Logger
from bootstrap.lib.options import Options
from bootstrap.run import init_logs_options_files
from block.datasets.vqa_utils import tokenize_mcb
if __name__ == "__main__":
Options()
#print("seed: {}".format(Options()['misc']['seed']))
utils.set_random_seed(Options()['misc']['seed'])
init_logs_options_files(Options()['exp']['dir'],
Options()['exp']['resume'])
engine = engines.factory()
#print("engine: {}".format(engine))
engine.dataset = datasets.factory(engine)
engine.model = models.factory(engine)
#print("engine.model: {}".format(engine.model))
engine.model.eval()
engine.resume()
#img_emb_module = load_img_emb_module().cuda() #engine.model.network.image_embedding
# inputs
img = torch.randn(1, 3, 224, 244).cuda()
question = 'What is the color of the white horse?'
question_words = tokenize_mcb(question)
question_wids = [
engine.dataset['eval'].word_to_wid[word] for word in question_words