Python cudnn.benchmark方法代碼示例

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def run(self):
        self.build_model()
        self.resume_and_evaluate()
        cudnn.benchmark = True
        
        for self.epoch in range(self.start_epoch, self.nb_epochs):
            self.train_1epoch()
            prec1, val_loss = self.validate_1epoch()
            is_best = prec1 > self.best_prec1
            #lr_scheduler
            self.scheduler.step(val_loss)
            # save model
            if is_best:
                self.best_prec1 = prec1
                with open('record/spatial/spatial_video_preds.pickle','wb') as f:
                    pickle.dump(self.dic_video_level_preds,f)
                f.close()
            
            save_checkpoint({
                'epoch': self.epoch,
                'state_dict': self.model.state_dict(),
                'best_prec1': self.best_prec1,
                'optimizer' : self.optimizer.state_dict()
            },is_best,'record/spatial/checkpoint.pth.tar','record/spatial/model_best.pth.tar') 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def main_inference():
    print("Loading config...")
    opt = TestOptions().parse()
    print("Loading dataset...")
    dset = TVQADataset(opt, mode=opt.mode)
    print("Loading model...")
    model = STAGE(opt)
    model.to(opt.device)
    cudnn.benchmark = True
    strict_mode = not opt.no_strict
    model_path = os.path.join("results", opt.model_dir, "best_valid.pth")
    model.load_state_dict(torch.load(model_path), strict=strict_mode)
    model.eval()
    model.inference_mode = True
    torch.set_grad_enabled(False)
    print("Evaluation Starts:\n")
    predictions = inference(opt, dset, model)
    print("predictions {}".format(predictions.keys()))
    pred_path = model_path.replace("best_valid.pth",
                                   "{}_inference_predictions.json".format(opt.mode))
    save_json(predictions, pred_path) 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def test_voc():
    # load net
    num_classes = len(VOC_CLASSES) + 1 # +1 background
    net = build_ssd('test', 300, num_classes) # initialize SSD
    net.load_state_dict(torch.load(args.trained_model))
    net.eval()
    print('Finished loading model!')
    # load data
    testset = VOCDetection(args.voc_root, [('2007', 'test')], None, VOCAnnotationTransform())
    if args.cuda:
        net = net.cuda()
        cudnn.benchmark = True
    # evaluation
    test_net(args.save_folder, net, args.cuda, testset,
             BaseTransform(net.size, (104, 117, 123)),
             thresh=args.visual_threshold) 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def extract_features(model, data_loader, print_freq=1, metric=None):
    cudnn.benchmark = False
    model.eval()
    batch_time = AverageMeter()
    data_time = AverageMeter()

    features = OrderedDict()
    labels = OrderedDict()
    fcs = OrderedDict()

    print("Begin to extract features...")
    for i, (imgs, fnames, pids, _, _) in enumerate(data_loader):
        _fcs, pool5s = extract_cnn_feature(model, imgs)
        for fname, fc, pool5, pid in zip(fnames, _fcs, pool5s, pids):
            features[fname] = pool5
            fcs[fname] = fc
            labels[fname] = pid
            
    cudnn.benchmark = True
    return features, labels, fcs   # 2048 pool5 feature, labels, 1024 fc layers 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def set_gpu(args, model):
    assert torch.cuda.is_available(), "CPU-only experiments currently unsupported"

    if args.gpu is not None:
        torch.cuda.set_device(args.gpu)
        model = model.cuda(args.gpu)
    elif args.multigpu is None:
        device = torch.device("cpu")
    else:
        # DataParallel will divide and allocate batch_size to all available GPUs
        print(f"=> Parallelizing on {args.multigpu} gpus")
        torch.cuda.set_device(args.multigpu[0])
        args.gpu = args.multigpu[0]
        model = torch.nn.DataParallel(model, device_ids=args.multigpu).cuda(
            args.multigpu[0]
        )

    cudnn.benchmark = True

    return model 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def main():
    cudnn.benchmark = False
    test_video=Test_video(short_side=[224,256])
    model = slowfastnet.resnet50(class_num=Config.CLASS_NUM)
    assert Config.LOAD_MODEL_PATH is not None
    print("load model from:", Config.LOAD_MODEL_PATH)
    pretrained_dict = torch.load(Config.LOAD_MODEL_PATH, map_location='cpu')
    try:
        model_dict = model.module.state_dict()
    except AttributeError:
        model_dict = model.state_dict()
    pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict}
    model_dict.update(pretrained_dict)
    model.load_state_dict(model_dict)
    model = model.cuda(params['gpu'][0])
    validation(model, test_video) 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def __init__(self, output_dir):
        if cfg.TRAIN.FLAG:
            self.model_dir = os.path.join(output_dir, 'Model')
            self.image_dir = os.path.join(output_dir, 'Image')
            self.log_dir = os.path.join(output_dir, 'Log')
            mkdir_p(self.model_dir)
            mkdir_p(self.image_dir)
            mkdir_p(self.log_dir)
            self.summary_writer = FileWriter(self.log_dir)

        self.max_epoch = cfg.TRAIN.MAX_EPOCH
        self.snapshot_interval = cfg.TRAIN.SNAPSHOT_INTERVAL

        s_gpus = cfg.GPU_ID.split(',')
        self.gpus = [int(ix) for ix in s_gpus]
        self.num_gpus = len(self.gpus)
        self.batch_size = cfg.TRAIN.BATCH_SIZE * self.num_gpus
        torch.cuda.set_device(self.gpus[0])
        cudnn.benchmark = True

    # ############# For training stageI GAN ############# 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def __init__(self, params, dist_model=False):
        model_params = params['module']
        self.model = models.modules.__dict__[params['module']['arch']](model_params)
        utils.init_weights(self.model, init_type='xavier')
        self.model.cuda()
        if dist_model:
            self.model = utils.DistModule(self.model)
            self.world_size = dist.get_world_size()
        else:
            self.model = models.modules.FixModule(self.model)
            self.world_size = 1

        if params['optim'] == 'SGD':
            self.optim = torch.optim.SGD(
                self.model.parameters(), lr=params['lr'],
                momentum=0.9, weight_decay=0.0001)
        elif params['optim'] == 'Adam':
            self.optim = torch.optim.Adam(
                self.model.parameters(), lr=params['lr'],
                betas=(params['beta1'], 0.999))
        else:   
            raise Exception("No such optimizer: {}".format(params['optim']))

        cudnn.benchmark = True 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def train(self):
        # cudnn.benchmark = True
        # self.__val()
        if self.configer.get('network', 'resume') is not None:
            if self.configer.get('network', 'resume_val'):
                self.__val(data_loader=self.data_loader.get_valloader(dataset='val'))
                return
            elif self.configer.get('network', 'resume_train'):
                self.__val(data_loader=self.data_loader.get_valloader(dataset='train'))
                return
            # return

        if self.configer.get('network', 'resume') is not None and self.configer.get('network', 'resume_val'):
            self.__val(data_loader=self.data_loader.get_valloader(dataset='val'))
            return

        while self.configer.get('iters') < self.configer.get('solver', 'max_iters'):
            self.__train()

        # use swa to average the model
        if 'swa' in self.configer.get('lr', 'lr_policy'):
            self.optimizer.swap_swa_sgd()
            self.optimizer.bn_update(self.train_loader, self.seg_net)

        self.__val(data_loader=self.data_loader.get_valloader(dataset='val')) 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def main():

    testset = DeployDataset(
        image_root=cfg.img_root,
        transform=BaseTransform(size=cfg.input_size, mean=cfg.means, std=cfg.stds)
    )
    test_loader = data.DataLoader(testset, batch_size=1, shuffle=False, num_workers=cfg.num_workers)

    # Model
    model = TextNet(is_training=False, backbone=cfg.net)
    model_path = os.path.join(cfg.save_dir, cfg.exp_name, \
              'textsnake_{}_{}.pth'.format(model.backbone_name, cfg.checkepoch))
    model.load_model(model_path)

    # copy to cuda
    model = model.to(cfg.device)
    if cfg.cuda:
        cudnn.benchmark = True
    detector = TextDetector(model, tr_thresh=cfg.tr_thresh, tcl_thresh=cfg.tcl_thresh)

    print('Start testing TextSnake.')
    output_dir = os.path.join(cfg.output_dir, cfg.exp_name)
    inference(detector, test_loader, output_dir) 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def initialize(self, fixed=None):

        # Parse options
        self.args = self.parse(fixed)

        # Setting default torch Tensor type
        if self.args.cuda and torch.cuda.is_available():
            torch.set_default_tensor_type('torch.cuda.FloatTensor')
            cudnn.benchmark = True
        else:
            torch.set_default_tensor_type('torch.FloatTensor')

        # Create weights saving directory
        if not os.path.exists(self.args.save_dir):
            os.mkdir(self.args.save_dir)

        # Create weights saving directory of target model
        model_save_path = os.path.join(self.args.save_dir, self.args.exp_name)

        if not os.path.exists(model_save_path):
            os.mkdir(model_save_path)

        return self.args 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def tes_net():
    # enable cudnn
    cudnn.benchmark = True

    # get the DataLoader
    data_loaders = get_loader(dataset_config, config, mode="test")

    #get the solver
    if args.model == 'cycleGAN':
        solver = Solver_cycleGAN(data_loaders, config, dataset_config)
    elif args.model =='makeupGAN':
        solver = Solver_makeupGAN(data_loaders, config, dataset_config)
    else:
        print("model that not support")
        exit()
    solver.test() 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def main(config):
    svhn_loader, mnist_loader = get_loader(config)
    
    solver = Solver(config, svhn_loader, mnist_loader)
    cudnn.benchmark = True 
    
    # create directories if not exist
    if not os.path.exists(config.model_path):
        os.makedirs(config.model_path)
    if not os.path.exists(config.sample_path):
        os.makedirs(config.sample_path)
    
    if config.mode == 'train':
        solver.train()
    elif config.mode == 'sample':
        solver.sample() 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def __init__(self, output_dir, data_loader, n_words, ixtoword, dataset):
        if cfg.TRAIN.FLAG:
            self.model_dir = os.path.join(output_dir, 'Model')
            self.image_dir = os.path.join(output_dir, 'Image')
            mkdir_p(self.model_dir)
            mkdir_p(self.image_dir)

        #torch.cuda.set_device(cfg.GPU_ID)
        #cudnn.benchmark = True

        self.batch_size = cfg.TRAIN.BATCH_SIZE
        self.max_epoch = cfg.TRAIN.MAX_EPOCH
        self.snapshot_interval = cfg.TRAIN.SNAPSHOT_INTERVAL

        self.n_words = n_words
        self.ixtoword = ixtoword
        self.data_loader = data_loader
        self.dataset = dataset
        self.num_batches = len(self.data_loader) 

# 需要導入模塊: from torch.backends import cudnn [as 別名]
# 或者: from torch.backends.cudnn import benchmark [as 別名]
def get_model(conf, num_class=10, data_parallel=True):
    name = conf['type']

    if name == 'wresnet40_2':
        model = WideResNet(40, 2, dropout_rate=0.0, num_classes=num_class)
    elif name == 'wresnet28_2':
        model = WideResNet(28, 2, dropout_rate=0.0, num_classes=num_class)
    elif name == 'wresnet28_10':
        model = WideResNet(28, 10, dropout_rate=0.0, num_classes=num_class)

    else:
        raise NameError('no model named, %s' % name)

    if data_parallel:
        model = model.cuda()
        model = DataParallel(model)
    else:
        import horovod.torch as hvd
        device = torch.device('cuda', hvd.local_rank())
        model = model.to(device)
    cudnn.benchmark = True
    return model