def test_calculate_frechet_distance(self): mu1, sigma1 = np.ones((16, )), np.ones((16, 16)) mu2, sigma2 = mu1 * 2, sigma1 * 2 score = fid_utils.calculate_frechet_distance(mu1=mu1, mu2=mu2, sigma1=sigma1, sigma2=sigma2) assert type(score) == np.float64 # Inputs check bad_mu2, bad_sigma2 = np.ones((15, 15)), np.ones((15, 15)) with pytest.raises(ValueError): fid_utils.calculate_frechet_distance(mu1=mu1, mu2=bad_mu2, sigma1=sigma1, sigma2=bad_sigma2)
def test_calculate_frechet_distance(self): mu1, sigma1 = np.ones((16, )), np.ones((16, 16)) mu2, sigma2 = mu1 * 2, sigma1 * 2 score = fid_utils.calculate_frechet_distance(mu1=mu1, mu2=mu2, sigma1=sigma1, sigma2=sigma2) assert type(score) == np.float64
def fid_score(num_real_samples, num_fake_samples, netG, dataset, seed=0, device=None, batch_size=50, verbose=True, stats_file=None, log_dir='./log'): """ Computes FID stats using functions that store images in memory for speed and fidelity. Fidelity since by storing images in memory, we don't subject the scores to different read/write implementations of imaging libraries. Args: num_real_samples (int): The number of real images to use for FID. num_fake_samples (int): The number of fake images to use for FID. netG (Module): Torch Module object representing the generator model. device (str/torch.device): Device identifier to use for computation. seed (int): The random seed to use. dataset (str/Dataset): The name of the dataset to load if known, or a custom Dataset object batch_size (int): The batch size to feedforward for inference. verbose (bool): If True, prints progress. stats_file (str): The statistics file to load from if there is already one. log_dir (str): Directory where feature statistics can be stored. Returns: float: Scalar FID score. """ start_time = time.time() # Check inputs if device is None: device = torch.device('cuda:0' if torch.cuda.is_available() else "cpu") if isinstance(dataset, str): default_datasets = { 'cifar10', 'cifar100', 'stl10_48', 'imagenet_32', 'imagenet_128', 'celeba_64', 'celeba_128', 'lsun_bedroom', 'fake_data', } if dataset not in default_datasets: raise ValueError('For default datasets, must be one of {}'.format( default_datasets)) elif issubclass(type(dataset), torch.utils.data.Dataset): if stats_file is None: raise ValueError( "stats_file to save/load from cannot be empty if using a custom dataset." ) if not stats_file.endswith('.npz'): stats_file = stats_file + '.npz' else: raise ValueError( 'dataset must be either a Dataset object or a string.') # Make sure the random seeds are fixed torch.manual_seed(seed) random.seed(seed) np.random.seed(seed) # Setup directories inception_path = os.path.join(log_dir, 'metrics', 'inception_model') # Setup the inception graph inception_utils.create_inception_graph(inception_path) # Start producing statistics for real and fake images # if device and device.index is not None: # # Avoid unbounded memory usage # gpu_options = tf.compat.v1.GPUOptions(allow_growth=True, # per_process_gpu_memory_fraction=0.15, # visible_device_list=str(device.index)) # config = tf.compat.v1.ConfigProto(gpu_options=gpu_options) # else: # config = tf.compat.v1.ConfigProto(device_count={'GPU': 0}) config = tf.compat.v1.ConfigProto() config.gpu_options.per_process_gpu_memory_fraction = 0.2 config.gpu_options.allow_growth = True with tf.compat.v1.Session(config=config) as sess: sess.run(tf.compat.v1.global_variables_initializer()) m_real, s_real = compute_real_dist_stats(num_samples=num_real_samples, sess=sess, dataset=dataset, batch_size=batch_size, verbose=verbose, stats_file=stats_file, log_dir=log_dir, seed=seed) m_fake, s_fake = compute_gen_dist_stats(netG=netG, num_samples=num_fake_samples, sess=sess, device=device, seed=seed, batch_size=batch_size, verbose=verbose) FID_score = fid_utils.calculate_frechet_distance(mu1=m_real, sigma1=s_real, mu2=m_fake, sigma2=s_fake) print("INFO: FID: {} [Time Taken: {:.4f} secs]".format( FID_score, time.time() - start_time)) return float(FID_score)
def fid_score(num_real_samples, num_fake_samples, netG, device, seed, dataset_name, batch_size=50, verbose=True, stats_file=None, log_dir='./log'): """ Computes FID stats using functions that store images in memory for speed and fidelity. Fidelity since by storing images in memory, we don't subject the scores to different read/write implementations of imaging libraries. Args: num_real_samples (int): The number of real images to use for FID. num_fake_samples (int): The number of fake images to use for FID. netG (Module): Torch Module object representing the generator model. device (str): Device identifier to use for computation. seed (int): The random seed to use. dataset_name (str): The name of the dataset to load. batch_size (int): The batch size to feedforward for inference. verbose (bool): If True, prints progress. stats_file (str): The statistics file to load from if there is already one. log_dir (str): Directory where feature statistics can be stored. Returns: float: Scalar FID score. """ start_time = time.time() # Make sure the random seeds are fixed torch.manual_seed(seed) random.seed(seed) np.random.seed(seed) # Setup directories inception_path = os.path.join(log_dir, 'metrics', 'inception_model') # Setup the inception graph inception_utils.create_inception_graph(inception_path) # Start producing statistics for real and fake images if device and device.index is not None: # Avoid unbounded memory usage gpu_options = tf.GPUOptions(allow_growth=True, per_process_gpu_memory_fraction=0.15, visible_device_list=str(device.index)) config = tf.ConfigProto(gpu_options=gpu_options) else: config = tf.ConfigProto(device_count={'GPU': 0}) with tf.Session(config=config) as sess: sess.run(tf.global_variables_initializer()) m_real, s_real = compute_real_dist_stats(num_samples=num_real_samples, sess=sess, dataset_name=dataset_name, batch_size=batch_size, verbose=verbose, stats_file=stats_file, log_dir=log_dir, seed=seed) m_fake, s_fake = compute_gen_dist_stats(netG=netG, num_samples=num_fake_samples, sess=sess, device=device, seed=seed, batch_size=batch_size, verbose=verbose) FID_score = fid_utils.calculate_frechet_distance(mu1=m_real, sigma1=s_real, mu2=m_fake, sigma2=s_fake) print("INFO: FID Score: {} [Time Taken: {:.4f} secs]".format( FID_score, time.time() - start_time)) return float(FID_score)