def get_transformer(config): normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) base_transformer = [T.ToTensor(), normalizer] if config.training is False: return T.Compose([T.Resize((config.height, config.width))] + base_transformer) if config.img_translation is None: return T.Compose([T.RandomSizedRectCrop(config.height, config.width), T.RandomHorizontalFlip()] + base_transformer) return T.Compose([T.RandomTranslateWithReflect(config.img_translation), T.RandomSizedRectCrop(config.height, config.width), T.RandomHorizontalFlip()] + base_transformer)
def get_data(name, split_id, data_dir, height, width, batch_size, workers, combine_trainval): root = osp.join(data_dir, name) dataset = datasets.create(name, root, split_id=split_id) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_set = dataset.trainval if combine_trainval else dataset.train num_classes = (dataset.num_trainval_ids if combine_trainval else dataset.num_train_ids) train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) test_transformer = T.Compose([ T.RectScale(height, width), T.ToTensor(), normalizer, ]) train_loader = DataLoader(Preprocessor(train_set, root=dataset.images_dir, transform=train_transformer), batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) val_loader = DataLoader(Preprocessor(dataset.val, root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) test_loader = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) pid_train = np.array(list(pid for _, pid, _ in train_set)) class_weight = np.array([(pid_train == i).sum() for i in range(num_classes)]) assert np.all(class_weight != 0) class_weight = pid_train.shape[0] / num_classes / class_weight class_weight = torch.Tensor(class_weight).cuda() return dataset, num_classes, class_weight, train_loader, val_loader, test_loader
def get_data(name, split_id, data_dir, height, width, batch_size, num_instances, workers, combine_trainval, batch_id): root = osp.join(data_dir, name) if name == 'synthetic': dataset = datasets.create(name, root, split_id=split_id, batch_id=batch_id) else: dataset = datasets.create(name, root, split_id=split_id) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_set = dataset.trainval if combine_trainval else dataset.train num_classes = (dataset.num_trainval_ids if combine_trainval else dataset.num_train_ids) train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) test_transformer = T.Compose([ T.RectScale(height, width), T.ToTensor(), normalizer, ]) train_loader = DataLoader(Preprocessor(train_set, root=dataset.images_dir, transform=train_transformer), batch_size=batch_size, num_workers=workers, sampler=RandomIdentitySampler( train_set, num_instances), pin_memory=True, drop_last=True) val_loader = DataLoader(Preprocessor(dataset.val, root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) test_loader = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) return dataset, num_classes, train_loader, val_loader, test_loader
def get_dataloader(dataset,data_dir, training=False, height=256, width=128, batch_size=64, workers=1): normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) if training: transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) else: transformer = T.Compose([ T.RectScale(height, width), T.ToTensor(), normalizer, ]) data_loader = DataLoader( Preprocessor(dataset, root=data_dir, transform=transformer), batch_size=batch_size, num_workers=workers, shuffle=training, pin_memory=True, drop_last=training) return data_loader
def get_loader(data, root, height=256, width=128, batch_size=32, workers=0, training=False): normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) if training: transformer = T.Compose([ T.RandomSizedRectCrop(height, width), # 对图像进行随机裁剪并缩放. T.RandomHorizontalFlip(), # 对给定的PIL.Image进行随机水平翻转,概率为0.5,属于数据增强. T.ToTensor(), # 将numpy图像转换为torch图像. normalizer, ]) else: transformer = T.Compose([ T.RectScale(height, width), # 缩放图像. T.ToTensor(), normalizer, ]) batch_size = batch_size * 8 data_loader = DataLoader(Preprocessor(data, root=root, transform=transformer), batch_size=batch_size, num_workers=workers, shuffle=training, pin_memory=True) return data_loader
def get_dataloader(self, dataset, training=False) : normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) if training: transformer = T.Compose([ T.RandomSizedRectCrop(self.data_height, self.data_width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) batch_size = self.batch_size else: transformer = T.Compose([ T.RectScale(self.data_height, self.data_width), T.ToTensor(), normalizer, ]) batch_size = self.eval_bs data_loader = DataLoader( Preprocessor(dataset, root=self.data_dir, transform=transformer, is_training=training, max_frames=self.max_frames), batch_size=batch_size, num_workers=self.data_workers, shuffle=training, pin_memory=True, drop_last=training) current_status = "Training" if training else "Test" print("create dataloader for {} with batch_size {}".format(current_status, batch_size)) return data_loader
def get_data(dataset_name, split_id, data_dir, batch_size, workers, num_instances, combine_trainval=False): root = osp.join(data_dir, dataset_name) dataset = get_dataset(dataset_name, root, split_id=split_id, num_val=1, download=True) normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_set = dataset.trainval if combine_trainval else dataset.train num_classes = (dataset.num_trainval_ids if combine_trainval else dataset.num_train_ids) train_processor = Preprocessor(train_set, root=dataset.images_dir, transform=transforms.Compose([ transforms.RandomSizedRectCrop(256, 128), transforms.RandomHorizontalFlip(), transforms.ToTensor(), normalizer, ])) if num_instances > 0: train_loader = DataLoader( train_processor, batch_size=batch_size, num_workers=workers, sampler=RandomIdentitySampler(train_set, num_instances), pin_memory=True) else: train_loader = DataLoader( train_processor, batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True) val_loader = DataLoader( Preprocessor(dataset.val, root=dataset.images_dir, transform=transforms.Compose([ transforms.RectScale(256, 128), transforms.ToTensor(), normalizer, ])), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) test_loader = DataLoader( Preprocessor(list(set(dataset.query) | set(dataset.gallery)), root=dataset.images_dir, transform=transforms.Compose([ transforms.RectScale(256, 128), transforms.ToTensor(), normalizer, ])), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) return dataset, num_classes, train_loader, val_loader, test_loader
def get_data(name, split_id, data_dir, height, width, batch_size, num_instances, workers, combine_trainval): root = osp.join(data_dir, name) dataset = datasets.create(name, root, split_id=split_id) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) # load train_set, query_set, gallery_set mt_train_set = dataset.train mt_num_classes = dataset.num_train_tids_sub query_set = dataset.query gallery_set = dataset.gallery train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer ]) test_transformer = T.Compose([ T.RectScale(height, width), T.ToTensor(), normalizer, ]) # Random ID mt_train_set = flatten_dataset(mt_train_set) num_task = len( mt_num_classes) # num_task equals camera number, each camera is a task mt_train_loader = DataLoader( Preprocessor_Image(mt_train_set, root=dataset.dataset_dir, transform=train_transformer), batch_size=batch_size, num_workers=workers, sampler=RandomIdentitySampler( mt_train_set, num_instances, num_task), # Here is different between softmax_loss pin_memory=True, drop_last=True) query_set = flatten_dataset(query_set) gallery_set = flatten_dataset(gallery_set) test_set = list(set(query_set) | set(gallery_set)) test_loader = DataLoader(Preprocessor_Image(test_set, root=dataset.dataset_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) return mt_train_loader, mt_num_classes, test_loader, query_set, gallery_set
def get_data(dataname, data_dir, height, width, batch_size, camstyle=0, re=0, workers=8): root = osp.join(data_dir, dataname) dataset = datasets.create(dataname, root) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) num_classes = dataset.num_train_ids train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, T.RandomErasing(EPSILON=re), ]) test_transformer = T.Compose([ T.Resize((height, width), interpolation=3), T.ToTensor(), normalizer, ]) train_loader = DataLoader( Preprocessor(dataset.train, root=osp.join(dataset.images_dir, dataset.train_path), transform=train_transformer), batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) query_loader = DataLoader( Preprocessor(dataset.query, root=osp.join(dataset.images_dir, dataset.query_path), transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) gallery_loader = DataLoader( Preprocessor(dataset.gallery, root=osp.join(dataset.images_dir, dataset.gallery_path), transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) if camstyle <= 0: camstyle_loader = None else: camstyle_loader = DataLoader( Preprocessor(dataset.camstyle, root=osp.join(dataset.images_dir, dataset.camstyle_path), transform=train_transformer), batch_size=camstyle, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) return dataset, num_classes, train_loader, query_loader, gallery_loader, camstyle_loader
def get_data(name, split_id, data_dir, height, width, batch_size, workers, combine_trainval, np_ratio): root = osp.join(data_dir, name) dataset = datasets.create(name, root, split_id=split_id) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_set = dataset.trainval if combine_trainval else dataset.train train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomSizedEarser(), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) test_transformer = T.Compose([ T.RectScale(height, width), T.ToTensor(), normalizer, ]) train_loader = DataLoader(Preprocessor(train_set, root=dataset.images_dir, transform=train_transformer), sampler=RandomPairSampler( train_set, neg_pos_ratio=np_ratio), batch_size=batch_size, num_workers=workers, pin_memory=False) val_loader = DataLoader(Preprocessor(dataset.val, root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=0, shuffle=False, pin_memory=False) test_loader = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=0, shuffle=False, pin_memory=False) return dataset, train_loader, val_loader, test_loader
def get_data(data_dir, source, target, height, width, batch_size, re=0, workers=8): dataset = DA(data_dir, source, target) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) num_classes = dataset.num_train_ids train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, T.RandomErasing(EPSILON=re), ]) test_transformer = T.Compose([ T.Resize((height, width), interpolation=3), T.ToTensor(), normalizer, ]) source_train_loader = DataLoader( Preprocessor(dataset.source_train, root=osp.join(dataset.source_images_dir, dataset.source_train_path), transform=train_transformer), batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) target_train_loader = DataLoader( UnsupervisedCamStylePreprocessor(dataset.target_train, root=osp.join(dataset.target_images_dir, dataset.target_train_path), camstyle_root=osp.join(dataset.target_images_dir, dataset.target_train_camstyle_path), num_cam=dataset.target_num_cam, transform=train_transformer), batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) query_loader = DataLoader( Preprocessor(dataset.query, root=osp.join(dataset.target_images_dir, dataset.query_path), transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) gallery_loader = DataLoader( Preprocessor(dataset.gallery, root=osp.join(dataset.target_images_dir, dataset.gallery_path), transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) return dataset, num_classes, source_train_loader, target_train_loader, query_loader, gallery_loader
def get_dataloader(self, dataset, training=False): normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) if training: # import transforms as T transformer = T.Compose([ T.RandomSizedRectCrop( self.data_height, self.data_width), # data_height = 256 data_width = 128 T.RandomHorizontalFlip(), # 随机水平翻转 T.ToTensor( ), # Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor. normalizer, # normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], # std=[0.229, 0.224, 0.225]) ]) batch_size = self.batch_size # batch_size = 16 else: transformer = T.Compose([ T.RectScale(self.data_height, self.data_width), # RectScale():三角缩放(?) T.ToTensor( ), # Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor. normalizer, # normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], ]) # std=[0.229, 0.224, 0.225]) batch_size = self.eval_bs # batch_size = 64 data_dir = self.data_dir # data_dir = dataset_all.image_dir data_loader = DataLoader( # DataLoader() Preprocessor( dataset, root=data_dir, num_samples=self. frames_per_video, # root = dataset_all.image_dir num_samples = 1 transform=transformer, is_training=training, max_frames=self.max_frames ), # transform = T.compose()返回值 is_training = False max_frames = 900 batch_size=batch_size, num_workers=self. data_workers, # batch_size = 16 data_workers = 6 shuffle=training, pin_memory=True, drop_last=training) # shuffle = True drop_last = True current_status = "Training" if training else "Testing" # current_status = 'Training' print("Create dataloader for {} with batch_size {}".format( current_status, batch_size)) # Create dataloader for Training with batch_size 16 return data_loader
def get_data(name, split_id, data_dir, height, width, batch_size, workers, combine_trainval): root = os.path.join(data_dir, name) dataset = datasets.create(name, root, split_id=split_id) train_set = dataset.trainval if combine_trainval else dataset.train num_classes = (dataset.num_trainval_ids if combine_trainval else dataset.num_train_ids) train_transformer = t.Compose([ t.RandomSizedRectCrop(height, width), t.RandomHorizontalFlip(), ColorHistograms() ]) test_transformer = t.Compose( [t.RectScale(height, width), ColorHistograms()]) train_loader = DataLoader(Preprocessor(train_set, root=dataset.images_dir, transform=train_transformer), batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) val_loader = DataLoader(Preprocessor(dataset.val, root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) test_loader = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) return dataset, num_classes, train_loader, val_loader, test_loader
def get_data(sourceName, mteName, split_id, data_dir, height, width, batch_size, workers, combine,num_instances=8): root = osp.join(data_dir, sourceName) rootMte = osp.join(data_dir, mteName) sourceSet = datasets.create(sourceName, root, num_val=0.1, split_id=split_id) mteSet = datasets.create(mteName, rootMte, num_val=0.1, split_id=split_id) num_classes = sourceSet.num_trainval_ids if combine else sourceSet.num_train_ids class_meta = mteSet.num_trainval_ids if combine else mteSet.num_train_ids normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) test_transformer = T.Compose([ T.RectScale(height, width), T.ToTensor(), normalizer, ]) defen_train_transformer = T.Compose([ Resize((height, width)), T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, T.RandomErasing(probability=0.5, sh=0.2, r1=0.3) ]) meta_train_loader = DataLoader( Preprocessor(sourceSet.trainval, root=sourceSet.images_dir, transform=defen_train_transformer), batch_size=batch_size, num_workers=workers, sampler=RandomIdentitySampler(sourceSet.trainval, num_instances), pin_memory=True, drop_last=True) meta_test_loader=DataLoader( Preprocessor(mteSet.trainval, root=mteSet.images_dir, transform=defen_train_transformer), batch_size=batch_size, num_workers=workers, sampler=RandomIdentitySampler(mteSet.trainval, num_instances), pin_memory=True, drop_last=True) sc_test_loader = DataLoader( Preprocessor(list(set(sourceSet.query) | set(sourceSet.gallery)), root=sourceSet.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) return sourceSet, mteSet, num_classes, meta_train_loader, meta_test_loader,sc_test_loader,class_meta
def get_dataloader(self, dataset, training=False): normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) if training: transformer = T.Compose([ T.RandomSizedRectCrop(self.data_height, self.data_width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, T.RandomErasing(probability=0.5, sh=0.2, r1=0.3) ]) else: transformer = T.Compose([ T.Resize((self.data_height, self.data_width)), T.ToTensor(), normalizer, ]) if training and self.num_classes == 0: data_loader = DataLoader(Preprocessor(dataset, root='', transform=transformer), batch_size=self.batch_size, num_workers=self.data_workers, sampler=RandomIdentitySampler( dataset, self.num_instances), pin_memory=True, drop_last=training) else: data_loader = DataLoader(Preprocessor(dataset, root='', transform=transformer), batch_size=self.batch_size, num_workers=self.data_workers, shuffle=training, pin_memory=True, drop_last=training) current_status = "Training" if training else "Test" print("create dataloader for {} with batch_size {}".format( current_status, self.batch_size)) return data_loader
def get_data(name, split_id, data_dir, height, width, batch_size, num_instances, workers, combine_trainval): root = osp.join(data_dir, name) dataset = datasets.create(name, root, split_id=split_id) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) # load train_set, query_set, gallery_set mt_train_set = dataset.train mt_num_classes = dataset.num_train_tids_sub query_set = dataset.query gallery_set = dataset.gallery train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer ]) test_transformer = T.Compose([ T.RectScale(height, width), T.ToTensor(), normalizer, ]) # Random ID mt_train_set = flatten_dataset(mt_train_set) num_task = len( mt_num_classes) # num_task equals camera number, each camera is a task mt_train_loader = DataLoader( Preprocessor_Image(mt_train_set, root=dataset.dataset_dir, transform=train_transformer), batch_size=batch_size, num_workers=workers, sampler=RandomIdentitySampler( mt_train_set, num_instances, num_task), # Here is different between softmax_loss pin_memory=True, drop_last=True) # correct format conflict query_set_new = [] for index in range(len(query_set)): img_paths = tuple(query_set[index][0]) tid = query_set[index][1] pid = query_set[index][2] tid_sub = query_set[index][3] pid_sub = query_set[index][4] camid = query_set[index][5] query_set_new.append((img_paths, tid, pid, tid_sub, pid_sub, camid)) gallery_set_new = [] for index in range(len(gallery_set)): img_paths = tuple(gallery_set[index][0]) tid = gallery_set[index][1] pid = gallery_set[index][2] tid_sub = gallery_set[index][3] pid_sub = gallery_set[index][4] camid = gallery_set[index][5] query_set_new.append((img_paths, tid, pid, tid_sub, pid_sub, camid)) test_set = list(set(query_set_new) | set(gallery_set_new)) seq_len = 16 test_loader = DataLoader(Preprocessor_Video(test_set, transform=test_transformer, seq_len=seq_len, sample='random'), batch_size=int(batch_size / seq_len), num_workers=workers, shuffle=False, pin_memory=True) return mt_train_loader, mt_num_classes, test_loader, query_set, gallery_set
def get_data(name, split_id, data_dir, height, width, batch_size, num_instances, workers, combine_trainval): root = osp.join(data_dir, name) dataset = datasets.create(name, root, split_id=split_id) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_set = dataset.trainval if combine_trainval else dataset.train num_classes = (dataset.num_trainval_ids if combine_trainval else dataset.num_train_ids) query = dataset.query query_ids = [pid for _, pid, _ in query] query_fnames = [fname for fname, _, _ in query] query_cams = [cam for _, _, cam in query] query_ids_unique = list(set(query_ids)) query_fnames_new, query_ids_new, query_cams_new = [], [], [] gallery_fnames_new, gallery_ids_new, gallery_cams_new = [], [], [] for k in query_ids_unique: idx = query_ids.index(k) query_ids_new.append(k) query_fnames_new.append(query_fnames[idx]) query_cams_new.append(query_cams[idx]) new_idx = idx + 1 while query_cams[idx] == query_cams[new_idx]: new_idx += 1 gallery_ids_new.append(k) gallery_fnames_new.append(query_fnames[new_idx]) gallery_cams_new.append(query_cams[new_idx]) query_num = len(query_ids_unique) query_test_num = 100 # 2 GPU split_num = query_num // query_test_num test_set = [] tmp = [] for k in range(split_num): for i in range(2): for j in range(k * query_test_num, (k + 1) * query_test_num): if i == 0: tmp.extend((query_fnames_new[j], query_ids_new[j], query_cams_new[j])) else: tmp.extend((gallery_fnames_new[j], gallery_ids_new[j], gallery_cams_new[j])) test_set.append(tmp) tmp = [] train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) test_transformer = T.Compose([ T.RectScale(height, width), T.ToTensor(), normalizer, ]) train_loader = DataLoader(Preprocessor(train_set, root=dataset.images_dir, transform=train_transformer), batch_size=batch_size, num_workers=workers, sampler=RandomIdentitySampler( train_set, num_instances), pin_memory=True, drop_last=True) val_loader = DataLoader(Preprocessor(dataset.val, root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) """ test_loader = DataLoader( Preprocessor(test_set, root=dataset.images_dir, transform=test_transformer), batch_size=2*query_test_num, num_workers=workers, shuffle=False, pin_memory=True) """ test_loader = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) return dataset, num_classes, train_loader, val_loader, test_loader
def main(args): np.random.seed(args.seed) torch.manual_seed(args.seed) cudnn.benchmark = True # Redirect print to both console and log file if not args.evaluate: sys.stdout = Logger(osp.join(args.logs_dir, 'log.txt')) # Create data loaders assert args.num_instances > 1, "num_instances should be greater than 1" assert args.batch_size % args.num_instances == 0, \ 'num_instances should divide batch_size' if args.height is None or args.width is None: args.height, args.width = (144, 56) if args.arch == 'inception' else \ (256, 128) train, val, trainval = [], [], [] numbers = [0, 0, 0] dataset_cuhk03 = merge('cuhk03', train, val, trainval, numbers, args.data_dir, args.split) dataset_market1501 = merge('market1501', train, val, trainval, numbers, args.data_dir, args.split) merge('cuhksysu', train, val, trainval, numbers, args.data_dir, args.split) merge('mars', train, val, trainval, numbers, args.data_dir, args.split) num_train_ids, num_val_ids, num_trainval_ids = numbers assert num_val_ids == dataset_cuhk03.num_val_ids + dataset_market1501.num_val_ids print("============================================") print("JSTL dataset loaded") print(" subset | # ids | # images") print(" ---------------------------") print(" train | {:5d} | {:8d}" .format(num_train_ids, len(train))) print(" val | {:5d} | {:8d}" .format(num_val_ids, len(val))) print(" trainval | {:5d} | {:8d}" .format(num_trainval_ids, len(trainval))) query_cuhk03, gallery_cuhk03 = dataset_cuhk03.query, dataset_cuhk03.gallery query_market1501, gallery_market1501 = dataset_market1501.query, dataset_market1501.gallery normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_set = trainval if args.combine_trainval else train num_classes = (num_trainval_ids if args.combine_trainval else num_train_ids) train_transformer = T.Compose([ T.RandomSizedRectCrop(args.height, args.width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) test_transformer = T.Compose([ T.RectScale(args.height, args.width), T.ToTensor(), normalizer, ]) train_loader = DataLoader( Preprocessor(train_set, root=args.data_dir, transform=train_transformer), batch_size=args.batch_size, num_workers=args.workers, sampler=RandomIdentitySampler(train_set, args.num_instances), pin_memory=True, drop_last=True) val_loader = DataLoader( Preprocessor(val, root=args.data_dir, transform=test_transformer), batch_size=args.batch_size, num_workers=args.workers, shuffle=False, pin_memory=True) test_loader_cuhk03 = DataLoader( Preprocessor(list(set(query_cuhk03) | set(gallery_cuhk03)), root=dataset_cuhk03.images_dir, transform=test_transformer), batch_size=args.batch_size, num_workers=args.workers, shuffle=False, pin_memory=True) test_loader_market1501 = DataLoader( Preprocessor(list(set(query_market1501) | set(gallery_market1501)), root=dataset_market1501.images_dir, transform=test_transformer), batch_size=args.batch_size, num_workers=args.workers, shuffle=False, pin_memory=True) # Create model # Hacking here to let the classifier be the last feature embedding layer # Net structure: avgpool -> FC(1024) -> FC(args.features) model = models.create(args.arch, num_features=1024, dropout=args.dropout, num_classes=args.features) # Load from checkpoint start_epoch = best_top1 = 0 if args.resume: checkpoint = load_checkpoint(args.resume) model.load_state_dict(checkpoint['state_dict']) start_epoch = checkpoint['epoch'] best_top1 = checkpoint['best_top1'] print("=> Start epoch {} best top1 {:.1%}" .format(start_epoch, best_top1)) model = nn.DataParallel(model).cuda() # Distance metric metric = DistanceMetric(algorithm=args.dist_metric) # Evaluator evaluator = Evaluator(model) if args.evaluate: metric.train(model, train_loader) print("Validation:") evaluator.evaluate(val_loader, val, val, metric) print("Test(cuhk03):") evaluator.evaluate(test_loader_cuhk03, query_cuhk03, gallery_cuhk03, metric) print("Test(market1501):") evaluator.evaluate(test_loader_market1501, query_market1501, gallery_market1501, metric) return # Criterion criterion = TripletLoss(margin=args.margin).cuda() # Optimizer optimizer = torch.optim.Adam(model.parameters(), lr=args.lr, weight_decay=args.weight_decay) # Trainer trainer = Trainer(model, criterion) # Schedule learning rate def adjust_lr(epoch): lr = args.lr if epoch <= 100 else \ args.lr * (0.001 ** ((epoch - 100) / 50.0)) for g in optimizer.param_groups: g['lr'] = lr * g.get('lr_mult', 1) # Start training for epoch in range(start_epoch, args.epochs): adjust_lr(epoch) trainer.train(epoch, train_loader, optimizer) if epoch < args.start_save: continue top1 = evaluator.evaluate(val_loader, val, val) is_best = top1 > best_top1 best_top1 = max(top1, best_top1) save_checkpoint({ 'state_dict': model.module.state_dict(), 'epoch': epoch + 1, 'best_top1': best_top1, }, is_best, fpath=osp.join(args.logs_dir, 'checkpoint.pth.tar')) print('\n * Finished epoch {:3d} top1: {:5.1%} best: {:5.1%}{}\n'. format(epoch, top1, best_top1, ' *' if is_best else '')) # Final test print('Test with best model:') checkpoint = load_checkpoint(osp.join(args.logs_dir, 'model_best.pth.tar')) model.module.load_state_dict(checkpoint['state_dict']) metric.train(model, train_loader) print("Test(cuhk03):") evaluator.evaluate(test_loader_cuhk03, query_cuhk03, gallery_cuhk03, metric) print("Test(market1501):") evaluator.evaluate(test_loader_market1501, query_market1501, gallery_market1501, metric)
def get_data(name, split_id, data_dir, height, width, batch_size, workers, combine_trainval): root = osp.join(data_dir, name) dataset = datasets.create(name, root, split_id=split_id) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_set = dataset.trainval if combine_trainval else dataset.train num_classes = (dataset.num_trainval_ids if combine_trainval else dataset.num_train_ids) train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) test_transformer = T.Compose([ T.RectScale(height, width), T.ToTensor(), normalizer, ]) train_loader = DataLoader( #images_dir = osp.join(self.root, 'images') Preprocessor(train_set, root=dataset.images_dir, transform=train_transformer), batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) train_loader_head = DataLoader(Preprocessor( train_set, root="/home/bfs/zty/reid_market/examples/data/cuhk03/images_head", transform=train_transformer), batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) train_loader_upper = DataLoader(Preprocessor( train_set, root="/home/bfs/zty/reid_market/examples/data/cuhk03/images_upper", transform=train_transformer), batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) train_loader_lower = DataLoader(Preprocessor( train_set, root="/home/bfs/zty/reid_market/examples/data/cuhk03/images_lower", transform=train_transformer), batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) val_loader = DataLoader(Preprocessor(dataset.val, root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) val_loader_head = DataLoader(Preprocessor( dataset.val, root="/home/bfs/zty/reid_market/examples/data/cuhk03/images_head", transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) val_loader_upper = DataLoader(Preprocessor( dataset.val, root="/home/bfs/zty/reid_market/examples/data/cuhk03/images_upper", transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) val_loader_lower = DataLoader(Preprocessor( dataset.val, root="/home/bfs/zty/reid_market/examples/data/cuhk03/images_lower", transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) test_loader = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) test_loader_head = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), root="/home/bfs/zty/reid_market/examples/data/cuhk03/images_head", transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) test_loader_upper = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), root="/home/bfs/zty/reid_market/examples/data/cuhk03/images_upper", transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) test_loader_lower = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), root="/home/bfs/zty/reid_market/examples/data/cuhk03/images_lower", transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) return dataset, num_classes, train_loader, train_loader_head, train_loader_upper, train_loader_lower,\ val_loader, val_loader_head, val_loader_upper, val_loader_lower, test_loader, test_loader_head, \ test_loader_upper, test_loader_lower
def get_data(name, split_id, data_dir, height, width, batch_size, num_instances, workers, combine_trainval, make_data): root = osp.join(data_dir, name) if make_data: from_dir1, from_dir2, num_eval, test, single = make_data if test == 'test': build_test = True test = '_test' elif test == 'train': build_test = False test = 'train' else: build_test = None test = '' to_dir = '{}{}{}{}{}'.format(from_dir1, from_dir2, num_eval, test, single) if single == 'single': single = True elif single == 'many': single = False else: print('must be either single or many') root = osp.join(data_dir, 'select') dataset = datasets.create(name, root, from_dir1=from_dir1, from_dir2=from_dir2, to_dir=to_dir, num_eval=int(num_eval), make_test=build_test, single=single, split_id=split_id) data_path = osp.join(root, 'datasets', to_dir) else: dataset = datasets.create(name, root, split_id=split_id) data_path = osp.join(root, 'datasets', name) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_set = dataset.trainval if combine_trainval else dataset.train num_classes = (dataset.num_trainval_ids if combine_trainval else dataset.num_train_ids) train_transformer = T.Compose([ T.RectCrop(height, width), # T.RectCrop(height / 2, width / 2), # effectively blurring # T.RectScale(int(height/2), int(width/2)), # T.RectScale(height, width), T.RandomSizedRectCrop(height, width, 0.4), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) test_transformer = T.Compose([ T.RectCrop(height, width), # T.RectScale(int(height / 2), int(width / 2 T.RectScale(height, width), T.ToTensor(), normalizer, ]) train_loader = DataLoader(Preprocessor(train_set, root=dataset.images_dir, transform=train_transformer), batch_size=batch_size, num_workers=workers, sampler=RandomIdentitySampler( train_set, num_instances), pin_memory=True, drop_last=True) val_loader = DataLoader( Preprocessor( dataset.val, root=dataset.images_dir, transform=test_transformer), # todo originally test_transformer batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) test_loader = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=True) return dataset, num_classes, train_loader, val_loader, test_loader, data_path
def get_data(name, split_id, data_dir, height, width, batch_size, workers, combine_trainval, np_ratio, model, instance_mode, eraser): root = osp.join(data_dir, name) dataset = datasets.create(name, root, split_id=split_id) normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_set = dataset.trainval if combine_trainval else dataset.train if eraser: train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomSizedEarser(), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) else: train_transformer = T.Compose([ T.RandomSizedRectCrop(height, width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) test_transformer = T.Compose([ T.RectScale(height, width), T.ToTensor(), normalizer, ]) if (model == 'Single'): video_dict = None if osp.isfile(osp.join(root, 'video.json')): video_dict = read_json(osp.join(root, 'video.json')) sampler = RandomTripletSampler(train_set, video_dict=None, skip_frames=10, inter_rate=0.9, inst_sample=instance_mode) elif (model == 'Siamese'): sampler = RandomPairSampler(train_set, neg_pos_ratio=np_ratio) else: raise ValueError('unrecognized mode') train_loader = DataLoader(Preprocessor(train_set, name, root=dataset.images_dir, transform=train_transformer), sampler=sampler, batch_size=batch_size, num_workers=workers, pin_memory=False) val_loader = DataLoader(Preprocessor(dataset.val, name, root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=False) test_loader = DataLoader(Preprocessor( list(set(dataset.query) | set(dataset.gallery)), name, root=dataset.images_dir, transform=test_transformer), batch_size=batch_size, num_workers=workers, shuffle=False, pin_memory=False) return dataset, train_loader, val_loader, test_loader
epoch = 0 normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) test_transformer = T.Compose([ T.RectScale(data_height, data_width), T.ToTensor(), normalizer, ]) # Get 'train_loader'. normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_transformer = T.Compose([ T.RandomSizedRectCrop(data_height, data_width), T.RandomHorizontalFlip(), T.ToTensor(), normalizer, ]) train_loader = DataLoader(Preprocessor(dataset.train, root=dataset.images_dir, transform=train_transformer), batch_size=batch_size, num_workers=workers, shuffle=True, pin_memory=True, drop_last=True) # Get 'optimizer'. if hasattr(model.module, 'base'): base_param_ids = set(map(id, model.module.base.parameters()))