從tea出發(fā)

start_time = datetime.datetime.now()args = parser.parse_args()

導(dǎo)入相關(guān)參數(shù)

num_class, args.train_list, args.val_list, prefix = dataset_config.return_dataset(args.dataset,args.modality)

從data_config.py中導(dǎo)出數(shù)據(jù)集的相關(guān)信息

full_arch_name = args.archif args.shift:full_arch_name += '_shift{}_{}'.format(args.shift_div, args.shift_place)args.store_name = '_'.join([args.experiment_name, args.dataset, args.modality, full_arch_name, args.consensus_type, 'segment%d' % args.num_segments,'e{}'.format(args.epochs)])if args.pretrain != 'imagenet':args.store_name += '_{}'.format(args.pretrain)if args.lr_type != 'step':args.store_name += '_{}'.format(args.lr_type)if args.dense_sample:args.store_name += '_dense'if args.suffix is not None:args.store_name += '_{}'.format(args.suffix)print('storing name: ' + args.store_name)

訓(xùn)練結(jié)果存儲(chǔ)

model = TSN(num_class, args.num_segments, args.modality,base_model=args.arch,consensus_type=args.consensus_type,dropout=args.dropout,img_feature_dim=args.img_feature_dim,partial_bn=not args.no_partialbn,pretrain=args.pretrain,is_shift=args.shift, shift_div=args.shift_div,shift_place=args.shift_place,fc_lr5=not (args.tune_from and args.dataset in args.tune_from),)

導(dǎo)入模型

crop_size = model.crop_sizescale_size = model.scale_sizeinput_mean = model.input_meaninput_std = model.input_stdpolicies = model.get_optim_policies()train_augmentation = model.get_augmentation(flip=False if 'something' in args.dataset else True)import pdb; pdb.set_trace()with torch.no_grad():model = torch.nn.DataParallel(model, device_ids=[0, 1]).cuda()#并行計(jì)算

相關(guān)參數(shù)導(dǎo)出及設(shè)置并行計(jì)算，其中GPU的數(shù)量由實(shí)際情況設(shè)置

# Add specific initialized lr and weight_decay for each groupfor param_group in policies:param_group['lr'] = args.lr * param_group['lr_mult']param_group['weight_decay'] = args.weight_decay * param_group['decay_mult']

設(shè)置初始化的學(xué)習(xí)率

optimizer = torch.optim.SGD(policies,momentum=args.momentum)

設(shè)置優(yōu)化器

if args.resume:#用來設(shè)置是否從斷點(diǎn)出繼續(xù)訓(xùn)練if os.path.isfile(args.resume):print(("=> loading checkpoint '{}'".format(args.resume)))checkpoint = torch.load(args.resume)args.start_epoch = checkpoint['epoch']best_prec1 = checkpoint['best_prec1']model.load_state_dict(checkpoint['state_dict'])optimizer.load_state_dict(checkpoint['optimizer'])print(("=> loaded checkpoint '{}' (epoch {})".format(args.evaluate, checkpoint['epoch'])))else:print(("=> no checkpoint found at '{}'".format(args.resume)))

通過預(yù)訓(xùn)練模型訓(xùn)練
…

總結(jié)

以上是生活随笔為你收集整理的解析复杂深度学习项目构建的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。