from datasets import get_cached_data parser = argparse.ArgumentParser() parser.add_argument('--cfg_file', type=str) parser.add_argument('--n_context', type=int, default=50) parser.add_argument('--seed', type=int, default=1234) parser.add_argument('--gpu', type=str, default='0') args = parser.parse_args() params = HParams(args.cfg_file) os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu np.random.seed(args.seed) tf.set_random_seed(args.seed) # data testset = get_cached_data(params, 'test') # model model = get_model(params) model.load() # run save_dir = f'{params.exp_dir}/evaluate/imfns_imputation/' os.makedirs(save_dir, exist_ok=True) log_file = open(f'{save_dir}/log.txt', 'w') def evaluate(batch): log_likel = model.execute(model.metric, batch) return -log_likel
from models import get_model from datasets import get_cached_data parser = argparse.ArgumentParser() parser.add_argument('--cfg_file', type=str) parser.add_argument('--seed', type=int, default=1234) parser.add_argument('--gpu', type=str, default='0') args = parser.parse_args() params = HParams(args.cfg_file) os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu np.random.seed(args.seed) tf.set_random_seed(args.seed) # data trainset = get_cached_data(params, 'train') atoms = np.array([1,6,7,8,9]) # model model = get_model(params) model.load() # run save_dir = f'{params.exp_dir}/evaluate/set_generation/' os.makedirs(save_dir, exist_ok=True) # train save_path = f'{save_dir}/train/' os.makedirs(save_path, exist_ok=True) res_p = defaultdict(list)
from models import get_model from datasets import get_cached_data parser = argparse.ArgumentParser() parser.add_argument('--cfg_file', type=str) parser.add_argument('--seed', type=int, default=1234) parser.add_argument('--gpu', type=str, default='0') args = parser.parse_args() params = HParams(args.cfg_file) os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu np.random.seed(args.seed) tf.set_random_seed(args.seed) # data validset = get_cached_data(params, 'valid') testset = get_cached_data(params, 'test') # model model = get_model(params) model.load() # run save_dir = f'{params.exp_dir}/evaluate/set_imputation/' os.makedirs(save_dir, exist_ok=True) log_file = open(f'{save_dir}/log.txt', 'w') def evaluate(batch): average_mse = [] for _ in range(5): sample = model.execute(model.sample, batch)
parser.add_argument('--n_points', type=int, default=128) parser.add_argument('--seed', type=int, default=1234) parser.add_argument('--gpu', type=str, default='0') args = parser.parse_args() params = HParams(args.cfg_file) # modify config params.dataset = 'modelnet' params.mask_type = 'det_expand' os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu np.random.seed(args.seed) tf.set_random_seed(args.seed) # data if not args.biased: validset = get_cached_data(params, 'valid') elif os.path.isfile('.modelnet_airplane_biased'): with open('.modelnet_airplane_biased', 'rb') as f: validset = pickle.load(f) else: with h5py.File('/data/pointcloud/ModelNet40_cloud.h5', 'r') as f: train_cloud = np.array(f['tr_cloud']) train_labels = np.array(f['tr_labels']) test_cloud = np.array(f['test_cloud']) test_labels = np.array(f['test_labels']) inds = np.where(test_labels == 0)[0] pcs = [] pcs_org = [] for i in inds: x = test_cloud[i].astype(np.float32) # preprocess