Python torch.LongTensor() Examples

def test_random_sampler_empty_pred():
    assigner = MaxIoUAssigner(
        pos_iou_thr=0.5,
        neg_iou_thr=0.5,
        ignore_iof_thr=0.5,
        ignore_wrt_candidates=False,
    )
    bboxes = torch.empty(0, 4)
    gt_bboxes = torch.FloatTensor([
        [0, 0, 10, 9],
        [0, 10, 10, 19],
    ])
    gt_labels = torch.LongTensor([1, 2])
    assign_result = assigner.assign(bboxes, gt_bboxes, gt_labels=gt_labels)

    sampler = RandomSampler(
        num=10, pos_fraction=0.5, neg_pos_ub=-1, add_gt_as_proposals=True)

    sample_result = sampler.sample(assign_result, bboxes, gt_bboxes, gt_labels)

    assert len(sample_result.pos_bboxes) == len(sample_result.pos_inds)
    assert len(sample_result.neg_bboxes) == len(sample_result.neg_inds) 

def forward(self, encoding, lengths):
        lengths = Variable(torch.LongTensor(lengths))
        if torch.cuda.is_available():
            lengths = lengths.cuda()
        if self.method == 'mean':
            encoding_pad = nn.utils.rnn.pack_padded_sequence(encoding, lengths.data.tolist(), batch_first=True)
            encoding = nn.utils.rnn.pad_packed_sequence(encoding_pad, batch_first=True, padding_value=0)[0]
            lengths = lengths.float().view(-1, 1)
            return encoding.sum(1) / lengths, None
        elif self.method == 'max':
            return encoding.max(1)  # [bsz, in_dim], [bsz, in_dim] (position)
        elif self.method == 'attn':
            size = encoding.size()  # [bsz, len, in_dim]
            x_flat = encoding.contiguous().view(-1, size[2])  # [bsz*len, in_dim]
            hbar = self.tanh(self.ws1(x_flat))  # [bsz*len, attn_hid]
            alphas = self.ws2(hbar).view(size[0], size[1])  # [bsz, len]
            alphas = nn.utils.rnn.pack_padded_sequence(alphas, lengths.data.tolist(), batch_first=True)
            alphas = nn.utils.rnn.pad_packed_sequence(alphas, batch_first=True, padding_value=-1e8)[0]
            alphas = functional.softmax(alphas, dim=1)  # [bsz, len]
            alphas = alphas.view(size[0], 1, size[1])  # [bsz, 1, len]
            return torch.bmm(alphas, encoding).squeeze(1), alphas  # [bsz, in_dim], [bsz, len]
        elif self.method == 'last':
            return torch.cat([encoding[i][lengths[i] - 1] for i in range(encoding.size(0))], dim=0), None 

def forward(self, input, target):
        features = self.feats(input)
        output_indices = list(range(0, (target.size(1))))
        # Iterate over fully connecteds for each imu, perform forward pass and
        # record the output.
        imu_out = []
        for i in self.imus:
            imu_i = getattr(self, 'imu{}'.format(i))
            imu_out.append(imu_i(features))
        # Add a singleton dim at 1 for sequence length, which is always 1 in
        # this model.
        output = torch.stack(imu_out, dim=1).unsqueeze(1)
        output /= output.norm(2, 3, keepdim=True)
        return torch.stack(
            imu_out,
            dim=1).unsqueeze(1), target, torch.LongTensor(output_indices) 

def shuffle_sequences(self, split="train", keys=None):
        if keys is None:
            # print(type(self.data))
            # print(type(self.data.keys()))
            keys = self.data[split].keys()

        for key in keys:
            if key in ["positive", "negative"]:
                continue
            idxs = list(range(len(self.data[split][key])))

            random.shuffle(idxs)

            self.sequences[split][key] = \
                self.sequences[split][key].index_select(
                    0, torch.LongTensor(idxs))

            temp = [self.data[split][key][i] for i in idxs]
            self.data[split][key] = temp

            temp = [self.masks[split][key][i] for i in idxs]
            self.masks[split][key] = temp 

def pose_inv_full(pose):
  '''
  param pose: N x 6
  Inverse the 2x3 transformer matrix.
  '''
  N, _ = pose.size()
  b = pose.view(N, 2, 3)[:, :, 2:]
  # A^{-1}
  # Calculate determinant
  determinant = (pose[:, 0] * pose[:, 4] - pose[:, 1] * pose[:, 3] + 1e-8).view(N, 1)
  indices = Variable(torch.LongTensor([4, 1, 3, 0]).cuda())
  scale = Variable(torch.Tensor([1, -1, -1, 1]).cuda())
  A_inv = torch.index_select(pose, 1, indices) * scale / determinant
  A_inv = A_inv.view(N, 2, 2)
  # b' = - A^{-1} b
  b_inv = - A_inv.matmul(b).view(N, 2, 1)
  transformer_inv = torch.cat([A_inv, b_inv], dim=2)
  return transformer_inv 

def get_aishell_data(data_dir, r):
    path = os.path.join(data_dir, 'transcript.txt')
    data_dir = os.path.join(data_dir, 'wav', 'train')
    wav_paths = []
    texts = []
    with open(path, 'r') as f:
        for line in f.readlines():
            items = line.strip().split('|')
            wav_paths.append(os.path.join(data_dir, items[0] + '.wav'))
            text = items[1]
            text = text_normalize(text) + 'E'
            text = [hp.char2idx[c] for c in text]
            text = torch.Tensor(text).type(torch.LongTensor)
            texts.append(text)

    for wav, txt in zip(wav_paths[-20:], texts[-20:]):
        print(wav, txt)

    return wav_paths[r], texts[r] 

def get_keda_data(dataset_dir, r):
    wav_paths = []
    texts = []

    wav_dirs = ['nannan', 'xiaofeng', 'donaldduck']
    csv_paths = ['transcript-nannan.csv', 'transcript-xiaofeng.csv', 'transcript-donaldduck.csv']
    for wav_dir, csv_path in zip(wav_dirs, csv_paths):
        csv = open(os.path.join(dataset_dir, csv_path), 'r')
        for line in csv.readlines():
            items = line.strip().split('|')
            wav_paths.append(os.path.join(dataset_dir, wav_dir, items[0] + '.wav'))
            text = text_normalize(items[1]) + 'E'
            text = [hp.char2idx[c] for c in text]
            text = torch.Tensor(text).type(torch.LongTensor)
            texts.append(text)
        csv.close()

    for wav in wav_paths[-20:]:
        print(wav)

    return wav_paths[r], texts[r] 

def get_LJ_data(data_dir, r):
    path = os.path.join(data_dir, 'transcript.csv')
    data_dir = os.path.join(data_dir, 'wavs')
    wav_paths = []
    texts = []
    with open(path, 'r') as f:
        for line in f.readlines():
            items = line.strip().split('|')
            wav_paths.append(os.path.join(data_dir, items[0] + '.wav'))
            text = items[1]
            text = text_normalize(text) + 'E'
            text = [hp.char2idx[c] for c in text]
            text = torch.Tensor(text).type(torch.LongTensor)
            texts.append(text)

    for wav in wav_paths[-20:]:
        print(wav)

    return wav_paths[r], texts[r] 

def set_conceptnet_inputs(input_event, relation, text_encoder, max_e1, max_r, force):
    abort = False

    e1_tokens, rel_tokens, _ = data.conceptnet_data.do_example(text_encoder, input_event, relation, None)

    if len(e1_tokens) >  max_e1:
        if force:
            XMB = torch.zeros(1, len(e1_tokens) + max_r).long().to(cfg.device)
        else:
            XMB = torch.zeros(1, max_e1 + max_r).long().to(cfg.device)
            return {}, True
    else:
        XMB = torch.zeros(1, max_e1 + max_r).long().to(cfg.device)

    XMB[:, :len(e1_tokens)] = torch.LongTensor(e1_tokens)
    XMB[:, max_e1:max_e1 + len(rel_tokens)] = torch.LongTensor(rel_tokens)

    batch = {}
    batch["sequences"] = XMB
    batch["attention_mask"] = data.conceptnet_data.make_attention_mask(XMB)

    return batch, abort 

def forward(self, input):
        # array has shape (N, 4, 1, 1000)
        # return the sequence + its RC concatenated
        # create inverted indices
        invert_dims = [1,3]
        input_bkup = input
        for idim in invert_dims:
            idxs = [i for i in range(input.size(idim)-1, -1, -1)]
            idxs_var = Variable(torch.LongTensor(idxs))
            if input.is_cuda:
                idxs_var =idxs_var.cuda()
            input = input.index_select(idim, idxs_var)
        #
        input = torch.cat([input_bkup, input], dim=0)
        #
        # Using numpy:
        #input = edit_tensor_in_numpy(input, lambda x: np.concatenate([x, x[:,::-1, : ,::-1]],axis=0))
        return input 

def test_max_iou_assigner():
    self = MaxIoUAssigner(
        pos_iou_thr=0.5,
        neg_iou_thr=0.5,
    )
    bboxes = torch.FloatTensor([
        [0, 0, 10, 10],
        [10, 10, 20, 20],
        [5, 5, 15, 15],
        [32, 32, 38, 42],
    ])
    gt_bboxes = torch.FloatTensor([
        [0, 0, 10, 9],
        [0, 10, 10, 19],
    ])
    gt_labels = torch.LongTensor([2, 3])
    assign_result = self.assign(bboxes, gt_bboxes, gt_labels=gt_labels)
    assert len(assign_result.gt_inds) == 4
    assert len(assign_result.labels) == 4

    expected_gt_inds = torch.LongTensor([1, 0, 2, 0])
    assert torch.all(assign_result.gt_inds == expected_gt_inds) 

def gen_base_anchors(self):
        """Generate base anchors.

        Returns:
            list(torch.Tensor): Base anchors of a feature grid in multiple
                feature levels.
        """
        multi_level_base_anchors = []
        for i, base_size in enumerate(self.base_sizes):
            base_anchors = self.gen_single_level_base_anchors(
                base_size,
                scales=self.scales[i],
                ratios=self.ratios[i],
                center=self.centers[i])
            indices = list(range(len(self.ratios[i])))
            indices.insert(1, len(indices))
            base_anchors = torch.index_select(base_anchors, 0,
                                              torch.LongTensor(indices))
            multi_level_base_anchors.append(base_anchors)
        return multi_level_base_anchors 

def test_max_iou_assigner_with_ignore():
    self = MaxIoUAssigner(
        pos_iou_thr=0.5,
        neg_iou_thr=0.5,
        ignore_iof_thr=0.5,
        ignore_wrt_candidates=False,
    )
    bboxes = torch.FloatTensor([
        [0, 0, 10, 10],
        [10, 10, 20, 20],
        [5, 5, 15, 15],
        [30, 32, 40, 42],
    ])
    gt_bboxes = torch.FloatTensor([
        [0, 0, 10, 9],
        [0, 10, 10, 19],
    ])
    gt_bboxes_ignore = torch.Tensor([
        [30, 30, 40, 40],
    ])
    assign_result = self.assign(
        bboxes, gt_bboxes, gt_bboxes_ignore=gt_bboxes_ignore)

    expected_gt_inds = torch.LongTensor([1, 0, 2, -1])
    assert torch.all(assign_result.gt_inds == expected_gt_inds) 

def get_blizzard_data(data_dir, r):
    file_list = './filelists/bliz13_audio_text_train_filelist.txt'

    texts = []
    wav_paths = []
    with open(file_list, 'r') as f:
        for line in f.readlines():
            wav_path, text = line.strip().split('|')
            wav_paths.append(os.path.join(data_dir, wav_path))

            text = text_normalize(text) + 'E'
            text = [hp.char2idx[c] for c in text]
            text = torch.Tensor(text).type(torch.LongTensor)
            texts.append(text)

    for wav in wav_paths[-20:]:
        print(wav)

    return wav_paths[r], texts[r] 

def __init__(self, args):
        super(ResNet18Image2IMUOneTower, self).__init__()
        assert args.sequence_length == 1, "ResNet18Image2IMU supports seq-len=1"

        self.class_weights = args.dataset.CLASS_WEIGHTS[torch.LongTensor(
            args.imus)]

        resnet_model = torchvision_resnet18(pretrained=args.pretrain)
        # Remove the last fully connected layer.
        del resnet_model.fc
        self.resnet = resnet_model

        self.resnet.conv1 = nn.Conv2d(6, 64, kernel_size=(7, 7), stride=(2, 2),
                                      padding=(3, 3), bias=False)

        num_features = 512
        num_frames = 1
        num_classes = args.num_classes
        # Make num_imu fc layers
        self.imus = args.imus
        for i in self.imus:
            setattr(self, 'imu{}'.format(i),
                    nn.Linear(num_frames * num_features, num_classes))
        self.dropout = nn.Dropout() 

def test_max_iou_assigner_with_empty_gt():
    """Test corner case where an image might have no true detections."""
    self = MaxIoUAssigner(
        pos_iou_thr=0.5,
        neg_iou_thr=0.5,
    )
    bboxes = torch.FloatTensor([
        [0, 0, 10, 10],
        [10, 10, 20, 20],
        [5, 5, 15, 15],
        [32, 32, 38, 42],
    ])
    gt_bboxes = torch.FloatTensor([])
    assign_result = self.assign(bboxes, gt_bboxes)

    expected_gt_inds = torch.LongTensor([0, 0, 0, 0])
    assert torch.all(assign_result.gt_inds == expected_gt_inds) 

def test_approx_iou_assigner():
    self = ApproxMaxIoUAssigner(
        pos_iou_thr=0.5,
        neg_iou_thr=0.5,
    )
    bboxes = torch.FloatTensor([
        [0, 0, 10, 10],
        [10, 10, 20, 20],
        [5, 5, 15, 15],
        [32, 32, 38, 42],
    ])
    gt_bboxes = torch.FloatTensor([
        [0, 0, 10, 9],
        [0, 10, 10, 19],
    ])
    approxs_per_octave = 1
    approxs = bboxes
    squares = bboxes
    assign_result = self.assign(approxs, squares, approxs_per_octave,
                                gt_bboxes)

    expected_gt_inds = torch.LongTensor([1, 0, 2, 0])
    assert torch.all(assign_result.gt_inds == expected_gt_inds) 

def test_approx_iou_assigner_with_empty_gt():
    """Test corner case where an image might have no true detections."""
    self = ApproxMaxIoUAssigner(
        pos_iou_thr=0.5,
        neg_iou_thr=0.5,
    )
    bboxes = torch.FloatTensor([
        [0, 0, 10, 10],
        [10, 10, 20, 20],
        [5, 5, 15, 15],
        [32, 32, 38, 42],
    ])
    gt_bboxes = torch.FloatTensor([])
    approxs_per_octave = 1
    approxs = bboxes
    squares = bboxes
    assign_result = self.assign(approxs, squares, approxs_per_octave,
                                gt_bboxes)

    expected_gt_inds = torch.LongTensor([0, 0, 0, 0])
    assert torch.all(assign_result.gt_inds == expected_gt_inds) 

def forward(self, input):
        # Swap ACGT to AGCT
        # array has shape (N, 4, 1, 1000)
        # pytorch doesn't support full indexing at the moment, at some point this should work: [:,:,torch.LongTensor([0,2,1,3])]
        input_reordered = [input[:,i,...] for i in [0,2,1,3]]
        input = torch.stack(input_reordered, dim=1)
        # slightly faster but ugly:
        #input = edit_tensor_in_numpy(input, lambda x: x[:,[0,2,1,3], ...])
        return input 

def validate(val_loader, model, criterion, evaluation, logger=None):
    losses = AverageMeter()
    accuracies = AverageMeter()

    # switch to evaluate mode
    model.eval()

    for i, (g, h, e, target) in enumerate(val_loader):

        # Prepare input data
        target = torch.squeeze(target).type(torch.LongTensor)
        if args.cuda:
            g, h, e, target = g.cuda(), h.cuda(), e.cuda(), target.cuda()
        g, h, e, target = Variable(g), Variable(h), Variable(e), Variable(target)

        # Compute output
        output = model(g, h, e)

        # Logs
        test_loss = criterion(output, target)
        acc = Variable(evaluation(output.data, target.data, topk=(1,))[0])

        losses.update(test_loss.data[0], g.size(0))
        accuracies.update(acc.data[0], g.size(0))

    print(' * Average Accuracy {acc.avg:.3f}; Average Loss {loss.avg:.3f}'
          .format(acc=accuracies, loss=losses))

    if logger is not None:
        logger.log_value('test_epoch_loss', losses.avg)
        logger.log_value('test_epoch_accuracy', accuracies.avg)

    return accuracies.avg 

def __getitem__(self, index):
        if self.mode == 'test':
            img_path, img_name = self.imgs[index]
            img = Image.open(os.path.join(img_path, img_name + '.jpg')).convert('RGB')
            if self.transform is not None:
                img = self.transform(img)
            return img_name, img

        img_path, mask_path = self.imgs[index]
        img = Image.open(img_path).convert('RGB')
        if self.mode == 'train':
            mask = sio.loadmat(mask_path)['GTcls']['Segmentation'][0][0]
            mask = Image.fromarray(mask.astype(np.uint8))
        else:
            mask = Image.open(mask_path)

        if self.joint_transform is not None:
            img, mask = self.joint_transform(img, mask)

        if self.sliding_crop is not None:
            img_slices, mask_slices, slices_info = self.sliding_crop(img, mask)
            if self.transform is not None:
                img_slices = [self.transform(e) for e in img_slices]
            if self.target_transform is not None:
                mask_slices = [self.target_transform(e) for e in mask_slices]
            img, mask = torch.stack(img_slices, 0), torch.stack(mask_slices, 0)
            return img, mask, torch.LongTensor(slices_info)
        else:
            if self.transform is not None:
                img = self.transform(img)
            if self.target_transform is not None:
                mask = self.target_transform(mask)
            return img, mask 

def forward(self, input, target):
        if self.training:
            raise RuntimeError("Can't do forward pass in training.")
        imu_start_index = 1 #inclusive
        imu_end_index = imu_start_index + self.planning_distance #exclusive
        assert imu_start_index > 0 and imu_end_index < self.sequence_length
        input_start = input[:, :imu_start_index]
        input_end = input[:, imu_end_index:]
        target = target[:, imu_start_index:imu_end_index]
        output_indices = list(range(imu_start_index, imu_end_index))
        input = torch.cat([input_start, input_end],1)

        input = input.data.contiguous().view(input.size(0), -1)
        new_tensor = input.new
        min_distances = new_tensor(input.size(0)).fill_(1e9)
        best_labels = new_tensor(target.size()).long().fill_(-1)
        for i, (train_data, train_label, _, _) in enumerate(self.train_loader):
            train_data_start = train_data[:, :imu_start_index]
            train_data_end = train_data[:, imu_end_index:]
            train_data = torch.cat([train_data_start, train_data_end],1).contiguous()
            train_data = train_data.view(train_data.size(0), -1).cuda(async=True)
            train_label = train_label[:, imu_start_index:imu_end_index].contiguous()
            train_label = train_label.cuda(async=True)

            distances = -torch.mm(input, train_data.t())
            cur_min_distances, min_indices = distances.min(1)
            min_indices = min_indices[:,None,None].expand_as(best_labels)
            cur_labels = train_label.gather(0, min_indices)
            old_new_distances = torch.stack([min_distances, cur_min_distances])
            min_distances, picker = old_new_distances.min(0)
            picker = picker[:,None,None].expand_as(best_labels)
            best_labels = (1 - picker) * best_labels + picker * cur_labels
        output = new_tensor(*best_labels.size(), self.num_classes).fill_(0)
        output.scatter_(3, best_labels.unsqueeze(3), 1)
        output = Variable(output)
        return output, target, torch.LongTensor(output_indices) 

def validate(val_loader, model, criterion, evaluation, logger=None):
    losses = AverageMeter()
    accuracies = AverageMeter()

    # switch to evaluate mode
    model.eval()

    end = time.time()
    for i, (g, h, e, target) in enumerate(val_loader):

        # Prepare input data
        target = torch.squeeze(target).type(torch.LongTensor)
        if args.cuda:
            g, h, e, target = g.cuda(), h.cuda(), e.cuda(), target.cuda()
        g, h, e, target = Variable(g), Variable(h), Variable(e), Variable(target)

        # Compute output
        output = model(g, h, e)

        # Logs
        test_loss = criterion(output, target)
        acc = Variable(evaluation(output.data, target.data, topk=(1,))[0])

        losses.update(test_loss.data[0], g.size(0))
        accuracies.update(acc.data[0], g.size(0))

    print(' * Average Accuracy {acc.avg:.3f}; Average Loss {loss.avg:.3f}'
          .format(acc=accuracies, loss=losses))

    if logger is not None:
        logger.log_value('test_epoch_loss', losses.avg)
        logger.log_value('test_epoch_accuracy', accuracies.avg)

    return accuracies.avg 

def validate(val_loader, model, criterion, evaluation, logger=None):
    losses = AverageMeter()
    accuracies = AverageMeter()

    # switch to evaluate mode
    model.eval()

    end = time.time()
    for i, (g, h, e, target) in enumerate(val_loader):

        # Prepare input data
        target = torch.squeeze(target).type(torch.LongTensor)
        if args.cuda:
            g, h, e, target = g.cuda(), h.cuda(), e.cuda(), target.cuda()
        g, h, e, target = Variable(g), Variable(h), Variable(e), Variable(target)

        # Compute output
        output = model(g, h, e)

        # Logs
        test_loss = criterion(output, target)
        acc = Variable(evaluation(output.data, target.data, topk=(1,))[0])

        losses.update(test_loss.data[0], g.size(0))
        accuracies.update(acc.data[0], g.size(0))

    print(' * Average Accuracy {acc.avg:.3f}; Average Loss {loss.avg:.3f}'
          .format(acc=accuracies, loss=losses))

    if logger is not None:
        logger.log_value('test_epoch_loss', losses.avg)
        logger.log_value('test_epoch_accuracy', accuracies.avg)

    return accuracies.avg 

def forward(self, input, target):
        features = self.feats(input)
        output_indices = list(range(0, (target.size(1))))
        # Iterate over fully connecteds for each imu, perform forward pass and
        # record the output.
        imu_out = []
        for i in self.imus:
            imu_i = getattr(self, 'imu{}'.format(i))
            imu_out.append(imu_i(features))
        # Add a singleton dim at 1 for sequence length, which is always 1 in
        # this model.
        return torch.stack(
            imu_out,
            dim=1).unsqueeze(1), target, torch.LongTensor(output_indices) 

def pth_nms(dets, thresh):
  """
  dets has to be a tensor
  """
  if not dets.is_cuda:
    x1 = dets[:, 0]
    y1 = dets[:, 1]
    x2 = dets[:, 2]
    y2 = dets[:, 3]
    scores = dets[:, 4]

    areas = (x2 - x1 + 1) * (y2 - y1 + 1)
    order = scores.sort(0, descending=True)[1]
    # order = torch.from_numpy(np.ascontiguousarray(scores.numpy().argsort()[::-1])).long()

    keep = torch.LongTensor(dets.size(0))
    num_out = torch.LongTensor(1)
    nms.cpu_nms(keep, num_out, dets, order, areas, thresh)

    return keep[:num_out[0]]
  else:
    x1 = dets[:, 0]
    y1 = dets[:, 1]
    x2 = dets[:, 2]
    y2 = dets[:, 3]
    scores = dets[:, 4]

    areas = (x2 - x1 + 1) * (y2 - y1 + 1)
    order = scores.sort(0, descending=True)[1]
    # order = torch.from_numpy(np.ascontiguousarray(scores.cpu().numpy().argsort()[::-1])).long().cuda()

    dets = dets[order].contiguous()

    keep = torch.LongTensor(dets.size(0))
    num_out = torch.LongTensor(1)
    # keep = torch.cuda.LongTensor(dets.size(0))
    # num_out = torch.cuda.LongTensor(1)
    nms.gpu_nms(keep, num_out, dets, thresh)

    return order[keep[:num_out[0]].cuda()].contiguous()
    # return order[keep[:num_out[0]]].contiguous() 

def validate(val_loader, model, criterion, evaluation, logger=None):
    losses = AverageMeter()
    accuracies = AverageMeter()

    # switch to evaluate mode
    model.eval()

    for i, (g, h, e, target) in enumerate(val_loader):

        # Prepare input data
        target = torch.squeeze(target).type(torch.LongTensor)
        if args.cuda:
            g, h, e, target = g.cuda(), h.cuda(), e.cuda(), target.cuda()
        g, h, e, target = Variable(g), Variable(h), Variable(e), Variable(target)

        # Compute output
        output = model(g, h, e)

        # Logs
        test_loss = criterion(output, target)
        acc = Variable(evaluation(output.data, target.data, topk=(1,))[0])

        losses.update(test_loss.data[0], g.size(0))
        accuracies.update(acc.data[0], g.size(0))

    print(' * Average Accuracy {acc.avg:.3f}; Average Loss {loss.avg:.3f}'
          .format(acc=accuracies, loss=losses))

    if logger is not None:
        logger.log_value('test_epoch_loss', losses.avg)
        logger.log_value('test_epoch_accuracy', accuracies.avg)

    return accuracies.avg 

def __init__(self, args):
        super(LstmImg2ActionPlanning, self).__init__()

        assert args.planning_distance == args.output_length

        self.input_length = args.input_length
        self.output_length = args.output_length
        self.sequence_length = args.sequence_length
        self.class_weights = args.dataset.CLASS_WEIGHTS[torch.LongTensor(
            args.imus)]
        self.planning_distance = args.planning_distance
        self.imus = args.imus
        self.hidden_size = args.hidden_size
        self.num_classes = args.num_classes

        self.embedding_input = nn.Linear(args.image_feature * 2,
                                         args.hidden_size)
        self.embedding_target = nn.Linear(args.num_classes * len(args.imus),
                                          args.hidden_size)
        self.lstm = nn.LSTMCell(args.hidden_size, args.hidden_size,
                                args.num_layers)
        self.out = nn.Linear(args.hidden_size, args.imu_feature)

        for i in self.imus:
            setattr(self, 'imu{}'.format(i),
                    nn.Linear(args.imu_feature, args.num_classes)) 

def validate(val_loader, model, criterion, evaluation, logger=None):
    losses = AverageMeter()
    accuracies = AverageMeter()

    # switch to evaluate mode
    model.eval()

    for i, (g, h, e, target) in enumerate(val_loader):

        # Prepare input data
        target = torch.squeeze(target).type(torch.LongTensor)
        if args.cuda:
            g, h, e, target = g.cuda(), h.cuda(), e.cuda(), target.cuda()
        g, h, e, target = Variable(g), Variable(h), Variable(e), Variable(target)

        # Compute output
        output = model(g, h, e)

        # Logs
        test_loss = criterion(output, target)
        acc = Variable(evaluation(output.data, target.data, topk=(1,))[0])

        losses.update(test_loss.data[0], g.size(0))
        accuracies.update(acc.data[0], g.size(0))

    print(' * Average Accuracy {acc.avg:.3f}; Average Loss {loss.avg:.3f}'
          .format(acc=accuracies, loss=losses))

    if logger is not None:
        logger.log_value('test_epoch_loss', losses.avg)
        logger.log_value('test_epoch_accuracy', accuracies.avg)

    return accuracies.avg 

def __init__(self, args):
        super(NearestNeighborPlanning, self).__init__()
        self.class_weights = args.dataset.CLASS_WEIGHTS[torch.LongTensor(
            args.imus)]
        self.planning_distance = args.planning_distance
        self.sequence_length = args.sequence_length
        self.train_loader = args.train_loader
        self.num_classes = args.num_classes