Python torch.no_grad方法代码示例

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def run(self):
        self.set_logger()

        # Initialize progress bar
        bar = utils.set_progress_bar(self.total_iters)

        for cycle_num in range(int(self.total_iters / self.iters)):
            self.model.train()

            self.cycle(bar, cycle_num)

            with torch.no_grad():
                self.run_evaluation_cycle()

            self.log_losses(self.opt, self.losses)
            self.update_top_score(self.opt)
            self.save_model(self.get_tracked_score())

        self.stop_logger() 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def hard_mining(self, inds, num_expected, bboxes, labels, feats):
        with torch.no_grad():
            rois = bbox2roi([bboxes])
            bbox_feats = self.bbox_roi_extractor(
                feats[:self.bbox_roi_extractor.num_inputs], rois)
            cls_score, _ = self.bbox_head(bbox_feats)
            loss = self.bbox_head.loss(
                cls_score=cls_score,
                bbox_pred=None,
                rois=rois,
                labels=labels,
                label_weights=cls_score.new_ones(cls_score.size(0)),
                bbox_targets=None,
                bbox_weights=None,
                reduction_override='none')['loss_cls']
            _, topk_loss_inds = loss.topk(num_expected)
        return inds[topk_loss_inds] 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        # encode mask results
        if isinstance(result, tuple):
            bbox_results, mask_results = result
            encoded_mask_results = encode_mask_results(mask_results)
            result = bbox_results, encoded_mask_results
        results.append(result)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def evaluate_accuracy(data_iter, net,
                      device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')):
    acc_sum, n = 0.0, 0
    with torch.no_grad():
        for X, y in data_iter:
            if isinstance(net, torch.nn.Module):
                net.eval() # 评估模式，会关闭 dropout
                acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()
                net.train() # 改回训练模式
            else:
                # 如果是自定义的模型
                if 'is_training' in net.__code__.co_varnames:
                    acc_sum += (net(X, is_training=False).argmax(dim=1) == y).float().sum().item()
                else:
                    acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
            n += y.shape[0]
    return acc_sum / n 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def predict(self, data, is_train=False) -> torch.Tensor or dict:
        """
        Make predict by data. If ``is_train`` is ``True`` - this operation will compute gradients. If
        ``is_train`` is ``False`` - this will work with ``model.eval()`` and ``torch.no_grad``

        :param data: data in dict
        :param is_train: is data processor need train on data or just predict
        :return: processed output
        :rtype: model return type
        """

        if is_train:
            self.model().train()
            output = self._model(self._pick_model_input(data))
        else:
            output = super().predict(data)

        return output 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def test(self, dataset):
        self.model.eval()
        with torch.no_grad():
            total_loss = 0.0
            predictions = torch.zeros(len(dataset), dtype=torch.float, device='cpu')
            indices = torch.arange(1, dataset.num_classes + 1, dtype=torch.float, device='cpu')
            for idx in tqdm(range(len(dataset)), desc='Testing epoch  ' + str(self.epoch) + ''):
                ltree, linput, rtree, rinput, label = dataset[idx]
                target = utils.map_label_to_target(label, dataset.num_classes)
                linput, rinput = linput.to(self.device), rinput.to(self.device)
                target = target.to(self.device)
                output = self.model(ltree, linput, rtree, rinput)
                loss = self.criterion(output, target)
                total_loss += loss.item()
                output = output.squeeze().to('cpu')
                predictions[idx] = torch.dot(indices, torch.exp(output))
        return total_loss / len(dataset), predictions 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def fuse_conv_and_bn(conv, bn):
    # https://tehnokv.com/posts/fusing-batchnorm-and-conv/
    with torch.no_grad():
        # init
        fusedconv = torch.nn.Conv2d(conv.in_channels,
                                    conv.out_channels,
                                    kernel_size=conv.kernel_size,
                                    stride=conv.stride,
                                    padding=conv.padding,
                                    bias=True)

        # prepare filters
        w_conv = conv.weight.clone().view(conv.out_channels, -1)
        w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
        fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.size()))

        # prepare spatial bias
        if conv.bias is not None:
            b_conv = conv.bias
        else:
            b_conv = torch.zeros(conv.weight.size(0))
        b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps))
        fusedconv.bias.copy_(b_conv + b_bn)

        return fusedconv 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def test(args, model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, size_average=False).item() # sum up batch loss
            pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset))) 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def select_action(self, state):
        """
        The action selection function, it either uses the model to choose an action or samples one uniformly.
        :param state: current state of the model
        :return:
        """
        if self.cuda:
            state = state.cuda()
        sample = random.random()
        eps_threshold = self.config.eps_start + (self.config.eps_start - self.config.eps_end) * math.exp(
            -1. * self.current_iteration / self.config.eps_decay)
        self.current_iteration += 1
        if sample > eps_threshold:
            with torch.no_grad():
                return self.policy_model(state).max(1)[1].view(1, 1)
        else:
            return torch.tensor([[random.randrange(2)]], device=self.device, dtype=torch.long) 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def validate(self):
        """
        One cycle of model validation
        :return:
        """
        self.model.eval()
        test_loss = 0
        correct = 0
        with torch.no_grad():
            for data, target in self.data_loader.test_loader:
                data, target = data.to(self.device), target.to(self.device)
                output = self.model(data)
                test_loss += F.nll_loss(output, target, size_average=False).item()  # sum up batch loss
                pred = output.max(1, keepdim=True)[1]  # get the index of the max log-probability
                correct += pred.eq(target.view_as(pred)).sum().item()

        test_loss /= len(self.data_loader.test_loader.dataset)
        self.logger.info('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
            test_loss, correct, len(self.data_loader.test_loader.dataset),
            100. * correct / len(self.data_loader.test_loader.dataset))) 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def extract_feature(model, model_path, dataloader, source, data_name):
    model.load_state_dict(torch.load(model_path))
    model.to(DEVICE)
    model.eval()
    fea = torch.zeros(1, 501).to(DEVICE)
    with torch.no_grad():
        for inputs, labels in dataloader:
            inputs, labels = inputs.to(DEVICE), labels.to(DEVICE)
            x = model.get_feature(inputs)
            x = x.view(x.size(0), -1)
            labels = labels.view(labels.size(0), 1).float()
            x = torch.cat((x, labels), dim=1)
            fea = torch.cat((fea, x), dim=0)
    fea_numpy = fea.cpu().numpy()
    np.savetxt('{}_{}.csv'.format(source, data_name), fea_numpy[1:], fmt='%.6f', delimiter=',')
    print('{} - {} done!'.format(source, data_name))


# You may want to use this function to simply classify them after getting features 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def extract_feature(model, dataloader, save_path, load_from_disk=True, model_path=''):
    if load_from_disk:
        model = models.Network(base_net=args.model_name,
                               n_class=args.num_class)
        model.load_state_dict(torch.load(model_path))
        model = model.to(DEVICE)
    model.eval()
    correct = 0
    fea_all = torch.zeros(1,1+model.base_network.output_num()).to(DEVICE)
    with torch.no_grad():
        for inputs, labels in dataloader:
            inputs, labels = inputs.to(DEVICE), labels.to(DEVICE)
            feas = model.get_features(inputs)
            labels = labels.view(labels.size(0), 1).float()
            x = torch.cat((feas, labels), dim=1)
            fea_all = torch.cat((fea_all, x), dim=0)
            outputs = model(inputs)
            preds = torch.max(outputs, 1)[1]
            correct += torch.sum(preds == labels.data.long())
        test_acc = correct.double() / len(dataloader.dataset)
    fea_numpy = fea_all.cpu().numpy()
    np.savetxt(save_path, fea_numpy[1:], fmt='%.6f', delimiter=',')
    print('Test acc: %f' % test_acc)

# You may want to classify with 1nn after getting features 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def test(model, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(DEVICE), target.to(DEVICE)
            out = model(data, data, target, DEVICE)
            s_output = out[0]
            test_loss += F.nll_loss(F.log_softmax(s_output, dim = 1), target, size_average=False).item() # sum up batch loss
            pred = s_output.data.max(1)[1] # get the index of the max log-probability
            correct += pred.eq(target.data.view_as(pred)).cpu().sum()

        test_loss /= len(test_loader.dataset)
        print(args.test_dir, '\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
            test_loss, correct, len(test_loader.dataset),
            100. * correct / len(test_loader.dataset)))
    return correct 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def test(model):
    model.eval()
    test_loss = 0
    correct = 0

    with torch.no_grad():
        for tgt_test_data, tgt_test_label in tgt_test_loader:
            if cuda:
                tgt_test_data, tgt_test_label = tgt_test_data.cuda(), tgt_test_label.cuda()
            tgt_test_data, tgt_test_label = Variable(tgt_test_data), Variable(tgt_test_label)
            tgt_pred, mmd_loss = model(tgt_test_data, tgt_test_data)
            test_loss += F.nll_loss(F.log_softmax(tgt_pred, dim = 1), tgt_test_label, reduction='sum').item() # sum up batch loss
            pred = tgt_pred.data.max(1)[1] # get the index of the max log-probability
            correct += pred.eq(tgt_test_label.data.view_as(pred)).cpu().sum()

    test_loss /= tgt_dataset_len
    print('\n{} set: Average loss: {:.4f}, Accuracy: {}/{} ({:.2f}%)\n'.format(
        tgt_name, test_loss, correct, tgt_dataset_len,
        100. * correct / tgt_dataset_len))
    return correct 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import no_grad [as 别名]
def test(model, target_test_loader):
    model.eval()
    test_loss = utils.AverageMeter()
    correct = 0
    criterion = torch.nn.CrossEntropyLoss()
    len_target_dataset = len(target_test_loader.dataset)
    with torch.no_grad():
        for data, target in target_test_loader:
            data, target = data.to(DEVICE), target.to(DEVICE)
            s_output = model.predict(data)
            loss = criterion(s_output, target)
            test_loss.update(loss.item())
            pred = torch.max(s_output, 1)[1]
            correct += torch.sum(pred == target)

    print('{} --> {}: max correct: {}, accuracy{: .2f}%\n'.format(
        source_name, target_name, correct, 100. * correct / len_target_dataset))