Function get_activations

src/pytorch_fid/fid_score.py:93–149

Calculates the activations of the pool_3 layer for all images. Params: -- files : List of image files paths -- model : Instance of inception model -- batch_size : Batch size of images for the model to process at once. Make sure that the number of sa

(files, model, batch_size=50, dims=2048, device='cpu',
                    num_workers=1)

def get_activations(files, model, batch_size=50, dims=2048, device='cpu',
                    num_workers=1):
    """Calculates the activations of the pool_3 layer for all images.

    Params:
    -- files       : List of image files paths
    -- model       : Instance of inception model
    -- batch_size  : Batch size of images for the model to process at once.
                     Make sure that the number of samples is a multiple of
                     the batch size, otherwise some samples are ignored. This
                     behavior is retained to match the original FID score
                     implementation.
    -- dims        : Dimensionality of features returned by Inception
    -- device      : Device to run calculations
    -- num_workers : Number of parallel dataloader workers

    Returns:
    -- A numpy array of dimension (num images, dims) that contains the
       activations of the given tensor when feeding inception with the
       query tensor.
    """
    model.eval()

    if batch_size > len(files):
        print(('Warning: batch size is bigger than the data size. '
               'Setting batch size to data size'))
        batch_size = len(files)

    dataset = ImagePathDataset(files, transforms=TF.ToTensor())
    dataloader = torch.utils.data.DataLoader(dataset,
                                             batch_size=batch_size,
                                             shuffle=False,
                                             drop_last=False,
                                             num_workers=num_workers)

    pred_arr = np.empty((len(files), dims))

    start_idx = 0

    for batch in tqdm(dataloader):
        batch = batch.to(device)

        with torch.no_grad():
            pred = model(batch)[0]

        # If model output is not scalar, apply global spatial average pooling.
        # This happens if you choose a dimensionality not equal 2048.
        if pred.size(2) != 1 or pred.size(3) != 1:
            pred = adaptive_avg_pool2d(pred, output_size=(1, 1))

        pred = pred.squeeze(3).squeeze(2).cpu().numpy()

        pred_arr[start_idx:start_idx + pred.shape[0]] = pred

        start_idx = start_idx + pred.shape[0]

    return pred_arr