def Img_transform(self, name, size, split='train'): assert (isinstance(size, tuple) and len(size) == 2) if name in ['CS', 'IDD', 'MAP', 'ADE', 'IDD20K']: if split == 'train': t = [ #transforms.RandomScale(1.1), #transforms.RandomRotate(3), #transforms.Resize((640,640)), #RandomAffine(1,(0.04,0.04),None,1,resample=Image.NEAREST,fillcolor=255), #Resize((512,512),Image.NEAREST), #RandomHorizontalFlip(), #ToTensor() transforms.Resize(size), #transforms.RandomCrop((512,512)), transforms.RandomHorizontalFlip(), transforms.ToTensor() ] else: t = [transforms.Resize(size), transforms.ToTensor()] return transforms.Compose(t) if split == 'train': t = [ transforms.Resize(size), transforms.RandomHorizontalFlip(), transforms.ToTensor() ] else: t = [transforms.Resize(size), transforms.ToTensor()] return transforms.Compose(t)
def Img_transform(self, name, size, split='train'): # if len(args.crop_size) == 1: # crop_size = (args.crop_size[0] , args.crop_size[0]) ## W x H # else: # crop_size = (args.crop_size[1] , args.crop_size[0]) assert (isinstance(size, tuple) and len(size) == 2) if name in ['CS', 'IDD']: if split == 'train': t = [ transforms.Resize(size), transforms.RandomCrop((512, 512)), transforms.RandomHorizontalFlip(), transforms.ToTensor() ] else: t = [transforms.Resize(size), transforms.ToTensor()] return transforms.Compose(t) if split == 'train': t = [ transforms.Resize(size), transforms.RandomHorizontalFlip(), transforms.ToTensor() ] else: t = [transforms.Resize(size), transforms.ToTensor()] return transforms.Compose(t)
def __init__(self, data, labels, is_train=True): super(Cifar10, self).__init__() self.data, self.labels = data, labels self.is_train = is_train assert len(self.data) == len(self.labels) mean, std = (0.4914, 0.4822, 0.4465), (0.2471, 0.2435, 0.2616) if is_train: self.trans_weak = T.Compose([ T.Resize((32, 32)), T.PadandRandomCrop(border=4, cropsize=(32, 32)), T.RandomHorizontalFlip(p=0.5), T.Normalize(mean, std), T.ToTensor(), ]) self.trans_strong = T.Compose([ T.Resize((32, 32)), T.PadandRandomCrop(border=4, cropsize=(32, 32)), T.RandomHorizontalFlip(p=0.5), RandomAugment(2, 10), T.Normalize(mean, std), T.ToTensor(), ]) else: self.trans = T.Compose([ T.Resize((32, 32)), T.Normalize(mean, std), T.ToTensor(), ])
def __init__(self, root, mode='train'): self.samples = [] lines = os.listdir(os.path.join(root, 'GT')) for line in lines: rgbpath = os.path.join(root, 'RGB', line[:-4] + '.jpg') tpath = os.path.join(root, 'T', line[:-4] + '.jpg') maskpath = os.path.join(root, 'GT', line) self.samples.append([rgbpath, tpath, maskpath]) if mode == 'train': self.transform = transform.Compose( transform.Normalize(mean1=mean_rgb, mean2=mean_t, std1=std_rgb, std2=std_t), transform.Resize(400, 400), transform.RandomHorizontalFlip(), transform.ToTensor()) elif mode == 'test': self.transform = transform.Compose( transform.Normalize(mean1=mean_rgb, mean2=mean_t, std1=std_rgb, std2=std_t), transform.Resize(400, 400), transform.ToTensor()) else: raise ValueError
def __init__(self, cfg): self.cfg = cfg if self.cfg.mode == 'train': self.transform = transform.Compose( transform.Normalize(mean=cfg.mean, std=cfg.std), transform.Resize(size=448), transform.RandomHorizontalFlip(), transform.ToTensor()) elif self.cfg.mode == 'test' or self.cfg.mode == 'val': self.transform = transform.Compose( transform.Normalize(mean=cfg.mean, std=cfg.std), transform.ToTensor()) else: raise ValueError
def getLoader(datasetName, dataroot, originalSize, imageSize, batchSize=64, workers=4, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), split='train', shuffle=True, seed=None): #import pdb; pdb.set_trace() if datasetName == 'folder': ########################### from pix2pix2 import folder_acquire as commonDataset import transform as transforms elif datasetName == 'list': from pix2pix2 import list_acquire as commonDataset import transform as transforms if split == 'train': dataset = commonDataset( root=dataroot, transform=transforms.Compose([ transforms.Scale(originalSize), # transforms.RandomCrop(imageSize), # transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize(mean, std), ]), seed=seed) else: dataset = commonDataset( root=dataroot, transform=transforms.Compose([ transforms.Scale(originalSize), # transforms.CenterCrop(imageSize), transforms.ToTensor(), transforms.Normalize(mean, std), ]), seed=seed) assert dataset ims = dataset.imgs ############################ dataloader = torch.utils.data.DataLoader(dataset, batch_size=batchSize, shuffle=shuffle, num_workers=int(workers)) return dataloader, ims ######################
def get_transform(train): transforms = [] transforms.append(T.ToTensor()) if train: transforms.append(T.RandomHorizontalFlip(0.5)) return T.Compose(transforms)
def load_PD_dataset(): tr = t.Transforms( (t.MagPhase(), t.PickChannel(0), t.Resize((1, 256, 256, 60, 8))), apply_to='image') tr = MultiModule((tr, t.ToTensor())) test = Split2d(PdDataset('../data/PD', transform=tr)) return test
def load_options(name, testing=False): """Saves experiment options under names to load in train and test""" if name == 'dncnn_mag': transform = t.Transforms((t.MagPhase(), t.PickChannel(0)), apply_to='both') transform = MultiModule(transform, t.Residual(), t.ToTensor()) train = Split2d(NiiDataset('../data/8echo/train', transform)) test = Split2d(NiiDataset('../data/8echo/test', transform)) model, depth, dropprob = DnCnn, 20, 0.0 optimizer = optim.Adam criterion = torch.nn.MSELoss() if name == 'dncnn_mag_patch': transform = t.Transforms((t.MagPhase(), t.PickChannel(0)), apply_to='both') transform = MultiModule(transform, t.Residual(), t.ToTensor()) train = SplitPatch(NiiDataset('../data/8echo/train', transform)) test = SplitPatch(NiiDataset('../data/8echo/test', transform)) model, depth, dropprob = DnCnn, 20, 0.0 optimizer = optim.Adam criterion = torch.nn.MSELoss() elif name == 'unet_mag': transform = t.Transforms((t.MagPhase(), t.PickChannel(0)), apply_to='both') transform = MultiModule(transform, t.Residual(), t.ToTensor()) train = Split2d(NiiDataset('../data/8echo/train', transform)) test = Split2d(NiiDataset('../data/8echo/test', transform)) model, depth, dropprob = UNet, 4, 0.0 optimizer = optim.Adamax criterion = torch.nn.MSELoss() if testing: # No dropout during testing dropprob = 0.0 example = train[0]['image'] in_size = example.shape[1:] in_ch = example.shape[0] model = model(in_size, in_ch, depth=depth, dropprob=dropprob) optimizer = optimizer(model.parameters()) return { 'dataset': (train, test), 'model': model, 'optimizer': optimizer, 'criterion': criterion }
def __init__(self, cfg): with open(cfg.datapath + '/' + cfg.mode + '.txt', 'r') as lines: self.samples = [] for line in lines: imagepath = cfg.datapath + '/image/' + line.strip() + '.jpg' maskpath = cfg.datapath + '/scribble/' + line.strip() + '.png' self.samples.append([imagepath, maskpath]) if cfg.mode == 'train': self.transform = transform.Compose( transform.Normalize(mean=cfg.mean, std=cfg.std), transform.Resize(320, 320), transform.RandomHorizontalFlip(), transform.RandomCrop(320, 320), transform.ToTensor()) elif cfg.mode == 'test': self.transform = transform.Compose( transform.Normalize(mean=cfg.mean, std=cfg.std), transform.Resize(320, 320), transform.ToTensor()) else: raise ValueError
def __init__(self, device="cuda:1"): picfile = str(time.strftime("%Y%m%d")) self.todaypath = os.path.join('/workspace/nologopics', picfile) if not os.path.exists(self.todaypath): os.mkdir(self.todaypath) self.device = torch.device(device) # logo检测模型 backbone = Backbone() self.ssdmodel = SSD300(backbone=backbone, num_classes=2) modelpath = './weights/ssd300-best.pth' weights_dict = torch.load(modelpath, map_location=device) self.ssdmodel.load_state_dict(weights_dict, strict=False) json_file = open('./pascal_voc_classes.json', 'r') class_dict = json.load(json_file) self.category_index = {v: k for k, v in class_dict.items()} self.data_transforms = transform.Compose([ transform.Resize(), transform.ToTensor(), transform.Normalization() ]) # 水印字体 self.font = ImageFont.truetype("./src/msyh.TTF", 24, encoding="utf-8") # 爬虫网址 self.spiderurl = { #clear_log 2: { 'url': 'http://adsoc.qknode.com/adagent/material/material?', 'topic': ["清理", "日历", "天气"] }, 0: { 'url': 'http://adsoc.qknode.com/adagent/material/center/rank?', 'topic': ["清理", "日历", "天气", "教育"] }, # 排行榜 1: { 'url': 'http://adsoc.qknode.com/adagent/material/material?', 'topic': ["清理", "日历", "天气"] } # 素材洞察 } # 推送地址 self.finalurl = 'http://adsoc.qknode.com/adagent/material/center/push' # self.cnniqamodel = CNNIQAnet(ker_size=7, n_kers=50, n1_nodes=800, n2_nodes=800) # self.cnniqamodel.load_state_dict(torch.load('./weights/CNNIQA-LIVE.pth',map_location=device)) if device != 'cpu': # self.cnniqamodel = self.cnniqamodel.to(self.device) # self.cnniqamodel.eval() self.ssdmodel = self.ssdmodel.to(self.device) self.ssdmodel.eval()
def img_transforms(img): img = np.array(img).astype(np.float32) sample = {'image': img} # img, label = random_crop(img, label, crop_size) transform = transforms.Compose([ # tr.FixedResize(img_size), tr.Normalize(mean=mean, std=std), tr.ToTensor() ]) sample = transform(sample) return sample['image']
def __init__(self, cfg): with open(os.path.join(cfg.datapath, cfg.mode + '.txt'), 'r') as lines: self.samples = [] for line in lines: imagepath = os.path.join(cfg.datapath, 'image', line.strip() + '.jpg') maskpath = os.path.join(cfg.datapath, 'mask', line.strip() + '.png') self.samples.append([imagepath, maskpath]) if cfg.mode == 'train': self.transform = transform.Compose( transform.Normalize(mean=cfg.mean, std=cfg.std), transform.Resize(320, 320), transform.RandomHorizontalFlip(), transform.RandomCrop(288, 288), transform.ToTensor()) elif cfg.mode == 'test': self.transform = transform.Compose( transform.Normalize(mean=cfg.mean, std=cfg.std), transform.Resize(320, 320), transform.ToTensor()) else: raise ValueError
def __init__(self, root, mode='train'): self.samples = [] lines = os.listdir(os.path.join(root, mode + '_images')) self.mode = mode for line in lines: rgbpath = os.path.join(root, mode + '_images', line) tpath = os.path.join(root, mode + '_depth', line[:-4] + '.png') maskpath = os.path.join(root, mode + '_masks', line[:-4] + '.png') self.samples.append([rgbpath, tpath, maskpath]) if mode == 'train': self.transform = transform.Compose( transform.Normalize(mean1=mean_rgb, std1=std_rgb), transform.Resize(256, 256), transform.RandomHorizontalFlip(), transform.ToTensor()) elif mode == 'test': self.transform = transform.Compose( transform.Normalize(mean1=mean_rgb, std1=std_rgb), transform.Resize(256, 256), transform.ToTensor()) else: raise ValueError
def __init__(self, data, labels, is_train=True): super(Cifar10, self).__init__() self.data, self.labels = data, labels self.is_train = is_train assert len(self.data) == len(self.labels) mean, std = (0.4914, 0.4822, 0.4465), (0.2471, 0.2435, 0.2616) # mean, std = (-0.0172, -0.0356, -0.1069), (0.4940, 0.4869, 0.5231) # [-1, 1] if is_train: self.trans_reg = transforms.Compose([ transforms.RandomResizedCrop(32), transforms.RandomHorizontalFlip(p=0.5), transforms.RandomApply( [transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)], p=0.8), transforms.RandomGrayscale(p=0.2), transforms.ToTensor(), transforms.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010]) ]) self.trans_weak = T.Compose([ T.Resize((32, 32)), T.PadandRandomCrop(border=4, cropsize=(32, 32)), T.RandomHorizontalFlip(p=0.5), T.Normalize(mean, std), T.ToTensor(), ]) self.trans_strong = T.Compose([ T.Resize((32, 32)), T.PadandRandomCrop(border=4, cropsize=(32, 32)), T.RandomHorizontalFlip(p=0.5), RandomAugment(2, 10), T.Normalize(mean, std), T.ToTensor(), ]) else: self.trans = T.Compose([ T.Resize((32, 32)), T.Normalize(mean, std), T.ToTensor(), ])
def __init__(self, data, labels, n_guesses=1, is_train=True): super(Cifar10, self).__init__() self.data, self.labels = data, labels self.n_guesses = n_guesses assert len(self.data) == len(self.labels) assert self.n_guesses >= 1 # mean, std = (0.4914, 0.4822, 0.4465), (0.2471, 0.2435, 0.2616) # [0, 1] mean, std = (-0.0172, -0.0356, -0.1069), (0.4940, 0.4869, 0.5231 ) # [-1, 1] if is_train: self.trans = T.Compose([ T.Resize((32, 32)), T.PadandRandomCrop(border=4, cropsize=(32, 32)), T.RandomHorizontalFlip(p=0.5), T.Normalize(mean, std), T.ToTensor(), ]) else: self.trans = T.Compose([ T.Resize((32, 32)), T.Normalize(mean, std), T.ToTensor(), ])
def main(): args, args = utils.get_args() ds = datasets.get_coco_kp(args.data_path, 'val', transform.ToTensor()) data_loader = torch.utils.data.DataLoader(ds, batch_size=2, collate_fn=collate_fn) eng = engine.Engine.command_line_init(args) model = torchvision.models.detection.keypointrcnn_resnet50_fpn( pretrained=True) model.to(eng.device) logger = Logger(eng.output_dir / 'keypoints_rcnn_val.json') eng.evaluate(model, data_loader, logger, 0) logger.dump()
def main(config): composed_transforms_ts = transforms.Compose([ transform.FixedResize(size=(config.input_size, config.input_size)), transform.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)), transform.ToTensor() ]) if config.mode == 'train': dataset = Dataset(datasets=['DAVIS'], transform=composed_transforms_ts, mode='train') train_loader = data.DataLoader(dataset, batch_size=config.batch_size, num_workers=config.num_thread, drop_last=True, shuffle=True) if not os.path.exists("%s/%s" % (config.save_fold, 'models')): os.mkdir("%s/%s" % (config.save_fold, 'models')) config.save_fold = "%s/%s" % (config.save_fold, 'models') train = Solver(train_loader, None, config) train.train() elif config.mode == 'test': dataset = Dataset(datasets=config.test_dataset, transform=composed_transforms_ts, mode='test') test_loader = data.DataLoader(dataset, batch_size=config.test_batch_size, num_workers=config.num_thread, drop_last=True, shuffle=False) test = Solver(train_loader=None, test_loader=test_loader, config=config, save_fold=config.testsavefold) test.test() else: raise IOError("illegal input!!!")
def main(): #数据集加载 dataset = Market1501() #训练数据处理器 transform_train = T.Compose([ T.Random2DTransform(height, width), #尺度统一,随机裁剪 T.RandomHorizontalFlip(), #水平翻转 T.ToTensor(), #图片转张量 T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), #归一化,参数固定 ]) #测试数据处理器 transform_test = T.Compose([ T.Resize((height, width)), #尺度统一 T.ToTensor(), #图片转张量 T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), #归一化,参数固定 ]) #train数据集吞吐器 train_data_loader = DataLoader( ImageDataset(dataset.train, transform=transform_train), #自定义的数据集,使用训练数据处理器 batch_size=train_batch_size, #一个批次的大小(一个批次有多少个图片张量) drop_last=True, #丢弃最后无法称为一整个批次的数据 ) print("train_data_loader inited") #query数据集吞吐器 query_data_loader = DataLoader( ImageDataset(dataset.query, transform=transform_test), #自定义的数据集,使用测试数据处理器 batch_size=test_batch_size, #一个批次的大小(一个批次有多少个图片张量) shuffle=False, #不重排 drop_last=True, #丢弃最后无法称为一整个批次的数据 ) print("query_data_loader inited") #gallery数据集吞吐器 gallery_data_loader = DataLoader( ImageDataset(dataset.gallery, transform=transform_test), #自定义的数据集,使用测试数据处理器 batch_size=test_batch_size, #一个批次的大小(一个批次有多少个图片张量) shuffle=False, #不重排 drop_last=True, #丢弃最后无法称为一整个批次的数据 ) print("gallery_data_loader inited\n") #加载模型 model = ReIDNet(num_classes=751, loss={'softmax'}) #指定分类的数量,与使用的损失函数以便决定模型输出何种计算结果 print("=>ReIDNet loaded") print("Model size: {:.5f}M\n".format( sum(p.numel() for p in model.parameters()) / 1000000.0)) #损失函数 criterion_class = nn.CrossEntropyLoss() """ 优化器 参数1,待优化的参数 参数2,学习率 参数3,权重衰减 """ optimizer = torch.optim.SGD(model.parameters(), lr=train_lr, weight_decay=5e-04) """ 动态学习率 参数1,指定使用的优化器 参数2,mode,可选择‘min’(min表示当监控量停止下降的时候,学习率将减小)或者‘max’(max表示当监控量停止上升的时候,学习率将减小) 参数3,factor,代表学习率每次降低多少 参数4,patience,容忍网路的性能不提升的次数,高于这个次数就降低学习率 参数5,min_lr,学习率的下限 """ scheduler = lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', factor=dy_step_gamma, patience=10, min_lr=0.0001) #如果是测试 if evaluate: test(model, query_data_loader, gallery_data_loader) return 0 #如果是训练 print('————model start training————\n') bt = time.time() #训练的开始时间 for epoch in range(start_epoch, end_epoch): model.train(True) train(epoch, model, criterion_class, optimizer, scheduler, train_data_loader) et = time.time() #训练的结束时间 print('**模型训练结束, 保存最终参数到{}**\n'.format(final_model_path)) torch.save(model.state_dict(), final_model_path) print('————训练总用时{:.2f}小时————'.format((et - bt) / 3600.0))
category_index = {} try: json_file = open('./pascal_voc_classes.json', 'r') class_dict = json.load(json_file) category_index = {v: k for k, v in class_dict.items()} except Exception as e: print(e) exit(-1) # load image original_img = Image.open("./test.jpg") # from pil image to tensor, do not normalize image data_transform = transform.Compose( [transform.Resize(), transform.ToTensor(), transform.Normalization()]) img, _ = data_transform(original_img) # expand batch dimension img = torch.unsqueeze(img, dim=0) model.eval() with torch.no_grad(): predictions = model( img.to(device))[0] # bboxes_out, labels_out, scores_out predict_boxes = predictions[0].to("cpu").numpy() predict_boxes[:, [0, 2]] = predict_boxes[:, [0, 2]] * original_img.size[0] predict_boxes[:, [1, 3]] = predict_boxes[:, [1, 3]] * original_img.size[1] predict_classes = predictions[1].to("cpu").numpy() predict_scores = predictions[2].to("cpu").numpy()
device_ids = args.devices.strip().split(',') device_ids = [int(device) for device in device_ids] lr = args.lr train_loss = args.loss epochs = args.epochs num_workers = args.num_workers batch_size = args.batch_size * len(device_ids) adam_param = tuple(map(float, args.adam_param.split(','))) pre_transform = RandomCrop(args.input_size, pad_if_needed=True) source_transform = transform.Compose([ # RandomGaussianNoise(p=0.95, mean=0, std=25, fixed_distribution=False), RandomTextOverlay(p=1, max_occupancy=30, length=(15, 30)), transform.ToTensor(), ]) target_transform = transform.Compose([ # RandomGaussianNoise(p=0.95, mean=0, std=25, fixed_distribution=False), RandomTextOverlay(p=1, max_occupancy=30, length=(15, 30)), transform.ToTensor(), ]) test_transform = transform.ToTensor() train_set = PairDataset(root_dir=os.path.join(args.data_path, 'train'), pre_transform=pre_transform, source_transform=source_transform, target_transform=target_transform) test_set = PairDataset(root_dir=os.path.join(args.data_path, 'test'), pre_transform=pre_transform, source_transform=source_transform, target_transform=test_transform)
def main(): device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") print(device) if not os.path.exists("save_weights"): os.mkdir("save_weights") data_transform = { "train": transform.Compose([transform.SSDCropping(), transform.Resize(), transform.ColorJitter(), transform.ToTensor(), transform.RandomHorizontalFlip(), transform.Normalization(), transform.AssignGTtoDefaultBox()]), "val": transform.Compose([transform.Resize(), transform.ToTensor(), transform.Normalization()]) } voc_path = "../" train_dataset = VOC2012DataSet(voc_path, data_transform['train'], True) # 注意训练时,batch_size必须大于1 train_data_loader = torch.utils.data.DataLoader(train_dataset, batch_size=8, shuffle=True, num_workers=0, collate_fn=utils.collate_fn) val_dataset = VOC2012DataSet(voc_path, data_transform['val'], False) val_data_loader = torch.utils.data.DataLoader(val_dataset, batch_size=1, shuffle=False, num_workers=0, collate_fn=utils.collate_fn) model = create_model(num_classes=21, device=device) model.to(device) # define optimizer params = [p for p in model.parameters() if p.requires_grad] optimizer = torch.optim.SGD(params, lr=0.002, momentum=0.9, weight_decay=0.0005) # learning rate scheduler lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.3) train_loss = [] learning_rate = [] val_map = [] val_data = None # 如果电脑内存充裕,可提前加载验证集数据,以免每次验证时都要重新加载一次数据,节省时间 # val_data = get_coco_api_from_dataset(val_data_loader.dataset) for epoch in range(20): utils.train_one_epoch(model=model, optimizer=optimizer, data_loader=train_data_loader, device=device, epoch=epoch, print_freq=50, train_loss=train_loss, train_lr=learning_rate, warmup=True) lr_scheduler.step() utils.evaluate(model=model, data_loader=val_data_loader, device=device, data_set=val_data, mAP_list=val_map) # save weights save_files = { 'model': model.state_dict(), 'optimizer': optimizer.state_dict(), 'lr_scheduler': lr_scheduler.state_dict(), 'epoch': epoch} torch.save(save_files, "./save_weights/ssd300-{}.pth".format(epoch)) # plot loss and lr curve if len(train_loss) != 0 and len(learning_rate) != 0: from plot_curve import plot_loss_and_lr plot_loss_and_lr(train_loss, learning_rate) # plot mAP curve if len(val_map) != 0: from plot_curve import plot_map plot_map(val_map)
def main(parser_data): device = torch.device( parser_data.device if torch.cuda.is_available() else "cpu") print("Using {} device training.".format(device.type)) if not os.path.exists("save_weights"): os.mkdir("save_weights") data_transform = { "train": transform.Compose([ transform.SSDCropping(), transform.Resize(), transform.ColorJitter(), transform.ToTensor(), transform.RandomHorizontalFlip(), transform.Normalization(), transform.AssignGTtoDefaultBox() ]), "val": transform.Compose([ transform.Resize(), transform.ToTensor(), transform.Normalization() ]) } VOC_root = parser_data.data_path # check voc root if os.path.exists(os.path.join(VOC_root, "VOCdevkit")) is False: raise FileNotFoundError( "VOCdevkit dose not in path:'{}'.".format(VOC_root)) train_dataset = VOC2012DataSet(VOC_root, data_transform['train'], train_set='train.txt') # 注意训练时,batch_size必须大于1 batch_size = parser_data.batch_size assert batch_size > 1, "batch size must be greater than 1" nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8]) # number of workers print('Using %g dataloader workers' % nw) train_data_loader = torch.utils.data.DataLoader( train_dataset, batch_size=batch_size, shuffle=True, num_workers=nw, collate_fn=train_dataset.collate_fn) val_dataset = VOC2012DataSet(VOC_root, data_transform['val'], train_set='val.txt') val_data_loader = torch.utils.data.DataLoader( val_dataset, batch_size=batch_size, shuffle=False, num_workers=nw, collate_fn=train_dataset.collate_fn) model = create_model(num_classes=21, device=device) model.to(device) # define optimizer params = [p for p in model.parameters() if p.requires_grad] optimizer = torch.optim.SGD(params, lr=0.0005, momentum=0.9, weight_decay=0.0005) # learning rate scheduler lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.3) # 如果指定了上次训练保存的权重文件地址,则接着上次结果接着训练 if parser_data.resume != "": checkpoint = torch.load(parser_data.resume) model.load_state_dict(checkpoint['model']) optimizer.load_state_dict(checkpoint['optimizer']) lr_scheduler.load_state_dict(checkpoint['lr_scheduler']) parser_data.start_epoch = checkpoint['epoch'] + 1 print("the training process from epoch{}...".format( parser_data.start_epoch)) train_loss = [] learning_rate = [] val_map = [] val_data = None # 如果电脑内存充裕,可提前加载验证集数据,以免每次验证时都要重新加载一次数据,节省时间 # val_data = get_coco_api_from_dataset(val_data_loader.dataset) for epoch in range(parser_data.start_epoch, parser_data.epochs): utils.train_one_epoch(model=model, optimizer=optimizer, data_loader=train_data_loader, device=device, epoch=epoch, print_freq=50, train_loss=train_loss, train_lr=learning_rate) lr_scheduler.step() utils.evaluate(model=model, data_loader=val_data_loader, device=device, data_set=val_data, mAP_list=val_map) # save weights save_files = { 'model': model.state_dict(), 'optimizer': optimizer.state_dict(), 'lr_scheduler': lr_scheduler.state_dict(), 'epoch': epoch } torch.save(save_files, "./save_weights/ssd300-{}.pth".format(epoch)) # plot loss and lr curve if len(train_loss) != 0 and len(learning_rate) != 0: from plot_curve import plot_loss_and_lr plot_loss_and_lr(train_loss, learning_rate) # plot mAP curve if len(val_map) != 0: from plot_curve import plot_map plot_map(val_map)
import utils import transform from datasets import GlucoseData from torch.utils.data import DataLoader import torch from torch import nn import models cgm_file, meals_file = utils.get_files() t = transform.ToTensor(categorical=GlucoseData.CATEGORICAL) train, val = GlucoseData.train_val_split(cgm_file, meals_file, transform=t) train_dl = DataLoader(train, batch_size=128, shuffle=True, collate_fn=utils.collate, num_workers=8) val_dl = DataLoader(val, batch_size=128, collate_fn=utils.collate, num_workers=8) model = models.BranchModel() criterion = nn.MSELoss() optimizer = torch.optim.Adam(model.parameters(), lr=1e-4, weight_decay=1e-2) def main(): for epoch in range(2): running_loss = 0.0 model.train() for i, samples in enumerate(train_dl): cgm = samples['cgm']
def main(args): print(args) # mp.spawn(main_worker, args=(args,), nprocs=args.world_size, join=True) init_distributed_mode(args) device = torch.device(args.device) results_file = "results{}.txt".format( datetime.datetime.now().strftime("%Y%m%d-%H%M%S")) # Data loading code print("Loading data") data_transform = { "train": transform.Compose([ transform.SSDCropping(), transform.Resize(), transform.ColorJitter(), transform.ToTensor(), transform.RandomHorizontalFlip(), transform.Normalization(), transform.AssignGTtoDefaultBox() ]), "val": transform.Compose([ transform.Resize(), transform.ToTensor(), transform.Normalization() ]) } VOC_root = args.data_path # check voc root if os.path.exists(os.path.join(VOC_root, "VOCdevkit")) is False: raise FileNotFoundError( "VOCdevkit dose not in path:'{}'.".format(VOC_root)) # load train data set train_data_set = VOC2012DataSet(VOC_root, data_transform["train"], train_set='train.txt') # load validation data set val_data_set = VOC2012DataSet(VOC_root, data_transform["val"], train_set='val.txt') print("Creating data loaders") if args.distributed: train_sampler = torch.utils.data.distributed.DistributedSampler( train_data_set) test_sampler = torch.utils.data.distributed.DistributedSampler( val_data_set) else: train_sampler = torch.utils.data.RandomSampler(train_data_set) test_sampler = torch.utils.data.SequentialSampler(val_data_set) if args.aspect_ratio_group_factor >= 0: # 统计所有图像比例在bins区间中的位置索引 group_ids = create_aspect_ratio_groups( train_data_set, k=args.aspect_ratio_group_factor) train_batch_sampler = GroupedBatchSampler(train_sampler, group_ids, args.batch_size) else: train_batch_sampler = torch.utils.data.BatchSampler(train_sampler, args.batch_size, drop_last=True) data_loader = torch.utils.data.DataLoader( train_data_set, batch_sampler=train_batch_sampler, num_workers=args.workers, collate_fn=train_data_set.collate_fn) data_loader_test = torch.utils.data.DataLoader( val_data_set, batch_size=1, sampler=test_sampler, num_workers=args.workers, collate_fn=train_data_set.collate_fn) print("Creating model") model = create_model(num_classes=args.num_classes + 1, device=device) model_without_ddp = model if args.distributed: model = torch.nn.parallel.DistributedDataParallel( model, device_ids=[args.gpu]) model_without_ddp = model.module params = [p for p in model.parameters() if p.requires_grad] optimizer = torch.optim.SGD(params, lr=args.lr, momentum=args.momentum, weight_decay=args.weight_decay) lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=args.lr_step_size, gamma=args.lr_gamma) # lr_scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=args.lr_steps, gamma=args.lr_gamma) # 如果传入resume参数,即上次训练的权重地址,则接着上次的参数训练 if args.resume: # If map_location is missing, torch.load will first load the module to CPU # and then copy each parameter to where it was saved, # which would result in all processes on the same machine using the same set of devices. checkpoint = torch.load( args.resume, map_location='cpu') # 读取之前保存的权重文件(包括优化器以及学习率策略) model_without_ddp.load_state_dict(checkpoint['model']) optimizer.load_state_dict(checkpoint['optimizer']) lr_scheduler.load_state_dict(checkpoint['lr_scheduler']) args.start_epoch = checkpoint['epoch'] + 1 if args.test_only: utils.evaluate(model, data_loader_test, device=device) return train_loss = [] learning_rate = [] val_map = [] print("Start training") start_time = time.time() for epoch in range(args.start_epoch, args.epochs): if args.distributed: train_sampler.set_epoch(epoch) mean_loss, lr = utils.train_one_epoch(model, optimizer, data_loader, device, epoch, args.print_freq) # only first process to save training info if args.rank in [-1, 0]: train_loss.append(mean_loss.item()) learning_rate.append(lr) # update learning rate lr_scheduler.step() # evaluate after every epoch coco_info = utils.evaluate(model, data_loader_test, device=device) if args.rank in [-1, 0]: # write into txt with open(results_file, "a") as f: result_info = [ str(round(i, 4)) for i in coco_info + [mean_loss.item(), lr] ] txt = "epoch:{} {}".format(epoch, ' '.join(result_info)) f.write(txt + "\n") val_map.append(coco_info[1]) # pascal mAP if args.output_dir: # 只在主节点上执行保存权重操作 save_on_master( { 'model': model_without_ddp.state_dict(), 'optimizer': optimizer.state_dict(), 'lr_scheduler': lr_scheduler.state_dict(), 'args': args, 'epoch': epoch }, os.path.join(args.output_dir, 'model_{}.pth'.format(epoch))) total_time = time.time() - start_time total_time_str = str(datetime.timedelta(seconds=int(total_time))) print('Training time {}'.format(total_time_str)) if args.rank in [-1, 0]: # plot loss and lr curve if len(train_loss) != 0 and len(learning_rate) != 0: from plot_curve import plot_loss_and_lr plot_loss_and_lr(train_loss, learning_rate) # plot mAP curve if len(val_map) != 0: from plot_curve import plot_map plot_map(val_map)
def load(self, filename): example = self.read(filename) example = self.transform(example) image, label = example return (t.ToTensor()(image), t.ToTensor()(label))
def main(args): print(args) # mp.spawn(main_worker, args=(args,), nprocs=args.world_size, join=True) utils.init_distributed_mode(args) device = torch.device(args.device) # Data loading code print("Loading data") data_transform = { "train": transform.Compose([ transform.SSDCropping(), transform.Resize(), # transform.ColorJitter(), transform.ToTensor(), transform.RandomHorizontalFlip(), transform.Normalization(), transform.AssignGTtoDefaultBox() ]), "val": transform.Compose([ transform.Resize(), transform.ToTensor(), transform.Normalization() ]) } VOC_root = args.data_path # load train data set train_data_set = VOC2012DataSet(VOC_root, data_transform["train"], True) # load validation data set val_data_set = VOC2012DataSet(VOC_root, data_transform["val"], False) print("Creating data loaders") if args.distributed: train_sampler = torch.utils.data.distributed.DistributedSampler( train_data_set) test_sampler = torch.utils.data.distributed.DistributedSampler( val_data_set) else: train_sampler = torch.utils.data.RandomSampler(train_data_set) test_sampler = torch.utils.data.SequentialSampler(val_data_set) if args.aspect_ratio_group_factor >= 0: # 统计所有图像比例在bins区间中的位置索引 group_ids = create_aspect_ratio_groups( train_data_set, k=args.aspect_ratio_group_factor) train_batch_sampler = GroupedBatchSampler(train_sampler, group_ids, args.batch_size) else: train_batch_sampler = torch.utils.data.BatchSampler(train_sampler, args.batch_size, drop_last=True) data_loader = torch.utils.data.DataLoader( train_data_set, batch_sampler=train_batch_sampler, num_workers=args.workers, collate_fn=utils.collate_fn) data_loader_test = torch.utils.data.DataLoader(val_data_set, batch_size=4, sampler=test_sampler, num_workers=args.workers, collate_fn=utils.collate_fn) print("Creating model") model = create_model(num_classes=21) model.to(device) model_without_ddp = model if args.distributed: model = torch.nn.parallel.DistributedDataParallel( model, device_ids=[args.gpu]) model_without_ddp = model.module params = [p for p in model.parameters() if p.requires_grad] optimizer = torch.optim.SGD(params, lr=args.lr, momentum=args.momentum, weight_decay=args.weight_decay) lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=args.lr_step_size, gamma=args.lr_gamma) # lr_scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=args.lr_steps, gamma=args.lr_gamma) # 如果传入resume参数,即上次训练的权重地址,则接着上次的参数训练 if args.resume: # If map_location is missing, torch.load will first load the module to CPU # and then copy each parameter to where it was saved, # which would result in all processes on the same machine using the same set of devices. checkpoint = torch.load( args.resume, map_location='cpu') # 读取之前保存的权重文件(包括优化器以及学习率策略) model_without_ddp.load_state_dict(checkpoint['model']) optimizer.load_state_dict(checkpoint['optimizer']) lr_scheduler.load_state_dict(checkpoint['lr_scheduler']) args.start_epoch = checkpoint['epoch'] + 1 if args.test_only: utils.evaluate(model, data_loader_test, device=device) return print("Start training") start_time = time.time() for epoch in range(args.start_epoch, args.epochs): if args.distributed: train_sampler.set_epoch(epoch) utils.train_one_epoch(model, optimizer, data_loader, device, epoch, args.print_freq) lr_scheduler.step() if args.output_dir: # 只在主节点上执行保存权重操作 utils.save_on_master( { 'model': model_without_ddp.state_dict(), 'optimizer': optimizer.state_dict(), 'lr_scheduler': lr_scheduler.state_dict(), 'args': args, 'epoch': epoch }, os.path.join(args.output_dir, 'model_{}.pth'.format(epoch))) # evaluate after every epoch utils.evaluate(model, data_loader_test, device=device) total_time = time.time() - start_time total_time_str = str(datetime.timedelta(seconds=int(total_time))) print('Training time {}'.format(total_time_str))
torch.distributed.init_process_group(backend='nccl', init_method='env://') synchronize() img_mean = [0.485, 0.456, 0.406] img_std = [0.229, 0.224, 0.225] device = 'cuda' # torch.backends.cudnn.deterministic = True train_trans = transform.Compose( [ transform.RandomScale(0.5, 2.0), # transform.Resize(args.size, None), transform.RandomHorizontalFlip(), transform.RandomCrop(args.size), transform.RandomBrightness(0.04), transform.ToTensor(), transform.Normalize(img_mean, img_std), transform.Pad(args.size) ] ) valid_trans = transform.Compose( [transform.ToTensor(), transform.Normalize(img_mean, img_std)] ) train_set = ADE20K(args.path, 'train', train_trans) valid_set = ADE20K(args.path, 'valid', valid_trans) arch_map = {'vovnet39': vovnet39, 'vovnet57': vovnet57} backbone = arch_map[args.arch](pretrained=True) model = OCR(args.n_class + 1, backbone).to(device)
def main(parser_data): device = torch.device( parser_data.device if torch.cuda.is_available() else "cpu") print(device) if not os.path.exists("save_weights"): os.mkdir("save_weights") data_transform = { "train": transform.Compose([ transform.SSDCropping(), transform.Resize(), transform.ColorJitter(), transform.ToTensor(), transform.RandomHorizontalFlip(), transform.Normalization(), transform.AssignGTtoDefaultBox() ]), "val": transform.Compose([ transform.Resize(), transform.ToTensor(), transform.Normalization() ]) } XRay_root = parser_data.data_path train_dataset = XRayDataset(XRay_root, data_transform['train'], train_set='train.txt') # Note that the batch_size must be greater than 1 train_data_loader = torch.utils.data.DataLoader( train_dataset, batch_size=8, shuffle=True, num_workers=4, collate_fn=utils.collate_fn) val_dataset = XRayDataset(XRay_root, data_transform['val'], train_set='val.txt') val_data_loader = torch.utils.data.DataLoader(val_dataset, batch_size=1, shuffle=False, num_workers=0, collate_fn=utils.collate_fn) model = create_model(num_classes=6, device=device) model.to(device) # define optimizer params = [p for p in model.parameters() if p.requires_grad] optimizer = torch.optim.SGD(params, lr=0.0005, momentum=0.9, weight_decay=0.0005) # learning rate scheduler lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.3) # If the address of the weight file saved by the last training is specified, the training continues with the last result if parser_data.resume != "": checkpoint = torch.load(parser_data.resume) model.load_state_dict(checkpoint['model']) optimizer.load_state_dict(checkpoint['optimizer']) lr_scheduler.load_state_dict(checkpoint['lr_scheduler']) parser_data.start_epoch = checkpoint['epoch'] + 1 print("the training process from epoch{}...".format( parser_data.start_epoch)) train_loss = [] learning_rate = [] val_map = [] val_data = None # If your computer has sufficient memory, you can save time by loading the validation set data in advance to avoid having to reload the data each time you validate # val_data = get_coco_api_from_dataset(val_data_loader.dataset) for epoch in range(parser_data.start_epoch, parser_data.epochs): utils.train_one_epoch(model=model, optimizer=optimizer, data_loader=train_data_loader, device=device, epoch=epoch, print_freq=50, train_loss=train_loss, train_lr=learning_rate) lr_scheduler.step() utils.evaluate(model=model, data_loader=val_data_loader, device=device, data_set=val_data, mAP_list=val_map) # save weights save_files = { 'model': model.state_dict(), 'optimizer': optimizer.state_dict(), 'lr_scheduler': lr_scheduler.state_dict(), 'epoch': epoch } torch.save(save_files, "./save_weights/ssd300-{}.pth".format(epoch)) # plot loss and lr curve if len(train_loss) != 0 and len(learning_rate) != 0: from plot_curve import plot_loss_and_lr plot_loss_and_lr(train_loss, learning_rate) # plot mAP curve if len(val_map) != 0: from plot_curve import plot_map plot_map(val_map)
def main(): print("------------------------------") print("START") print("------------------------------") composed_transforms_tr = standard_transforms.Compose([ tr.RandomHorizontalFlip(), tr.ScaleNRotate(rots=(-15, 15), scales=(.75, 1.5)), # tr.RandomResizedCrop(img_size), tr.FixedResize(img_size), tr.Normalize(mean=mean, std=std), tr.ToTensor() ]) # data pocessing and data augumentation voc_train_dataset = VOCSegmentation( base_dir=data_dir, split='train', transform=composed_transforms_tr) # get data #return {'image': _img, 'gt': _target} print("Data loaded...") print("Dataset:{}".format(dataset)) print("------------------------------") voc_train_loader = DataLoader(voc_train_dataset, batch_size=batch_size, shuffle=True, num_workers=1) iter_dataset = iter(voc_train_loader) train = next(iter_dataset) print("Input size {}".format(train['image'].shape)) print("Output size {}".format(train['gt'].shape)) print("Model start training...") print("------------------------------") print("Model info:") print("If use CUDA : {}".format(use_gpu)) print('Initial learning rate {} | batch size {} | epoch num {}'.format( 0.0001, batch_size, epoches)) print("------------------------------") model = fpn_unet(input_bands=input_bands, n_classes=num_class) model_id = 0 # load model if find_new_file(model_dir) is not None: model.load_state_dict(torch.load(find_new_file(model_dir))) # model.load_state_dict(torch.load('./pth/best2.pth')) print('load the model %s' % find_new_file(model_dir)) model_id = re.findall(r'\d+', find_new_file(model_dir)) model_id = int(model_id[0]) print('Current model ID {}'.format(model_id)) model.cuda() criterion = torch.nn.CrossEntropyLoss() #define loss optimizer = torch.optim.Adam(model.parameters(), lr=0.0001) #define optimizer model.cuda() model.train() f = open('log.txt', 'w') for epoch in range(epoches): cur_log = '' running_loss = 0.0 start = time.time() lr = adjust_learning_rate(base_lr, optimizer, epoch, model_id, power) print("Current learning rate : {}".format(lr)) for i, batch_data in tqdm.tqdm(enumerate(voc_train_loader)): #get data images, labels = batch_data['image'], batch_data['gt'] labels = labels.view(images.size()[0], img_size, img_size).long() i += images.size()[0] images = Variable(images).cuda() labels = Variable(labels).cuda() optimizer.zero_grad() outputs = model(images) losses = criterion(outputs, labels) # calculate loss losses.backward() optimizer.step() running_loss += losses print("Epoch [%d] all Loss: %.4f" % (epoch + 1 + model_id, running_loss / i)) cur_log += 'epoch:{}, '.format(str(epoch)) + 'learning_rate:{}'.format( str(lr)) + ', ' + 'train_loss:{}'.format( str(running_loss.item() / i)) + ', ' torch.save(model.state_dict(), os.path.join(model_dir, '%d.pth' % (model_id + epoch + 1))) print("Model Saved") # iou, acc, recall, precision = test_my(input_bands, model_name, model_dir, img_size, num_class) # cur_log += 'iou:{}'.format(str(iou)) + ', ' + 'acc:{}'.format(str(acc))+'\n' + ', ' + 'recall:{}'.format(str(recall))+'\n' + ', ' + 'precision:{}'.format(str(precision)) end = time.time() time_cha = end - start left_steps = epoches - epoch - model_id print('the left time is %d hours, and %d minutes' % (int(left_steps * time_cha) / 3600, (int(left_steps * time_cha) % 3600) / 60)) print(cur_log) f.writelines(str(cur_log))