def __init__(self, mode='train'):
"""
初始化函数
"""
assert mode in ['train', 'test',
'valid'], 'mode is one of train, test, valid.'
self.data = []
with open('signs/{}.txt'.format(mode)) as f:
for line in f.readlines():
info = line.strip().split('\t')
if len(info) > 0:
self.data.append([info[0].strip(), info[1].strip()])
if mode == 'train':
self.transforms = T.Compose([
T.RandomResizedCrop(IMAGE_SIZE), # 随机裁剪大小
T.RandomHorizontalFlip(0.5), # 随机水平翻转
T.ToTensor(), # 数据的格式转换和标准化 HWC => CHW
T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 图像归一化
])
else:
self.transforms = T.Compose([
T.Resize(256), # 图像大小修改
T.RandomCrop(IMAGE_SIZE), # 随机裁剪
T.ToTensor(), # 数据的格式转换和标准化 HWC => CHW
T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 图像归一化
])
def __init__(self, mode="train"):
super(HumanClasDataset, self).__init__()
self.data_path = data_dir
ps = os.listdir(osp.join(self.data_path, "p"))
ns = os.listdir(osp.join(self.data_path, "n"))
ps.sort()
ns.sort()
ps = [osp.join("p", x) for x in ps]
ns = [osp.join("n", x) for x in ns]
ns = random.sample(ns, len(ps))
data = []
if mode == "train":
for idx in range(int(len(ps) * 0.8)):
data.append([ps[idx], 1])
for idx in range(int(len(ns) * 0.8)):
data.append([ns[idx], 0])
else:
for idx in range(int(len(ps) * 0.8), len(ps)):
data.append([ps[idx], 1])
for idx in range(int(len(ns) * 0.8), len(ns)):
data.append([ns[idx], 0])
self.data = data
self.transform = vt.Compose([
vt.ColorJitter(0.1, 0.1, 0.1, 0.1),
# # vt.RandomRotation(10),
vt.RandomHorizontalFlip(),
vt.Resize(64),
vt.ToTensor(),
]) # TODO: 研究合适的数据增强策略
def main(_):
transform = T.Compose([T.ToTensor(), T.Normalize(mean=0.5, std=0.5)])
train_img_path = []
train_label = []
train_dataset = MyDataset(image=train_img_path,
lable=train_label,
transform=transform)
train_loader = paddle.io.DataLoader(train_dataset,
places=paddle.CPUPlace(),
batch_size=2,
shuffle=True)
model = resnet18(pretrained=True, num_classes=102, with_pool=True)
model = paddle.Model(model)
optim = paddle.optimizer.Adam(learning_rate=0.001,
parameters=model.parameters())
"""Train or evaluates the model."""
if FLAGS.mode == 'train':
model.prepare(
optimizer=optim,
loss=paddle.nn.MSELoss(),
metric=Accuracy() # topk计算准确率的top个数，默认是1
)
model.fit(
train_loader,
epochs=2,
verbose=1,
)
model.evaluate(train_dataset, batch_size=2, verbose=1)
model.save('inference_model', training=False)
elif FLAGS.mode == 'eval_rollout':
metadata = _read_metadata(FLAGS.data_path)
def prepare_train_data(self, index):
img_path = self.img_paths[index]
gt_path = self.gt_paths[index]
img = get_img(img_path, self.read_type)
bboxes, words = get_ann(img, gt_path)
# max line in gt
if bboxes.shape[0] > self.max_word_num:
bboxes = bboxes[:self.max_word_num]
words = words[:self.max_word_num]
if self.is_transform:
img = random_scale(img, self.short_size)
gt_instance = np.zeros(img.shape[0:2], dtype='uint8')
training_mask = np.ones(img.shape[0:2], dtype='uint8')
if bboxes.shape[0] > 0: # line
bboxes = np.reshape(bboxes * ([img.shape[1], img.shape[0]] * 4),
(bboxes.shape[0], -1, 2)).astype('int32')
for i in range(bboxes.shape[0]):
cv2.drawContours(gt_instance, [bboxes[i]], -1, i + 1, -1)
if words[i] == '###':
cv2.drawContours(training_mask, [bboxes[i]], -1, 0, -1)
gt_kernels = []
for i in range(1, self.kernel_num):
rate = 1.0 - (1.0 - self.min_scale) / (self.kernel_num - 1) * i
gt_kernel = np.zeros(img.shape[0:2], dtype='uint8')
kernel_bboxes = shrink(bboxes, rate)
for i in range(bboxes.shape[0]):
cv2.drawContours(gt_kernel, [kernel_bboxes[i].astype(int)], -1, 1, -1)
gt_kernels.append(gt_kernel)
if self.is_transform:
imgs = [img, gt_instance, training_mask]
imgs.extend(gt_kernels)
if not self.with_rec:
imgs = random_horizontal_flip(imgs)
imgs = random_rotate(imgs)
imgs = random_crop_padding(imgs, self.img_size)
img, gt_instance, training_mask, gt_kernels = imgs[0], imgs[1], imgs[2], imgs[3:]
gt_text = gt_instance.copy()
gt_text[gt_text > 0] = 1
gt_kernels = np.array(gt_kernels)
img = Image.fromarray(img)
img = img.convert('RGB')
if self.is_transform:
img = transforms.ColorJitter(brightness=32.0 / 255, saturation=0.5)(img)
img = transforms.ToTensor()(img)
img = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])(img)
gt_text = paddle.to_tensor(gt_text,dtype="int64")
gt_kernels = paddle.to_tensor(gt_kernels,dtype="int64")
training_mask = paddle.to_tensor(training_mask,dtype="int64")
return img.numpy(),gt_text.numpy(),gt_kernels.numpy(),training_mask.numpy()
def get_transforms(resize, crop):
transforms = T.Compose([
T.Resize(resize, interpolation="bicubic"),
T.CenterCrop(crop),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
return transforms
def get_transforms(resize, crop):
transforms = [T.Resize(resize, interpolation="bicubic")]
if crop:
transforms.append(T.CenterCrop(crop))
transforms.append(T.ToTensor())
transforms.append(
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
transforms = T.Compose(transforms)
return transforms
def get_transforms(interpolation):
transforms = T.Compose(
[
T.Resize(256, interpolation=interpolation),
T.CenterCrop(224),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
]
)
return transforms
def __init__(self, config, need_parser=True):
self.img_size = 256
self.transform = transform = T.Compose([
T.Resize(size=256),
T.ToTensor(),
])
self.norm = T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
if need_parser:
self.face_parser = futils.mask.FaceParser()
self.up_ratio = 0.6 / 0.85
self.down_ratio = 0.2 / 0.85
self.width_ratio = 0.2 / 0.85
def __init__(self, model_path, use_cuda=True):
self.net = Net(reid=True)
self.device = "cuda" if use_cuda else "cpu"
state_dict = torch.load(model_path)
self.net.set_state_dict(state_dict)
logger = logging.getLogger("root.tracker")
logger.info("Loading weights from {}... Done!".format(model_path))
# self.net.to(self.device)
self.size = (64, 128)
self.norm = transforms.Compose([
transforms.ToTensor(data_format='HWC'),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225], data_format='HWC'),
])
def get_dataloader(self, num_workers):
dataset = paddle.vision.datasets.MNIST(
mode='test',
transform=transforms.Compose([
transforms.CenterCrop(20),
transforms.RandomResizedCrop(14),
transforms.Normalize(),
transforms.ToTensor()
]))
loader = paddle.io.DataLoader(dataset,
batch_size=32,
num_workers=num_workers,
shuffle=True)
return loader
def __init__(self, root_dir, label_file, is_bin=True):
super(CommonDataset, self).__init__()
self.root_dir = root_dir
self.label_file = label_file
self.full_lines = self.get_file_list(label_file)
self.delimiter = "\t"
self.is_bin = is_bin
self.transform = transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
])
self.num_samples = len(self.full_lines)
def prepare_test_data(self, index):
img_path = self.img_paths[index]
img = get_img(img_path, self.read_type)
img_meta = dict(org_img_size=np.array(img.shape[:2]))
img = scale_aligned_short(img, self.short_size)
img_meta.update(dict(img_size=np.array(img.shape[:2])))
img = Image.fromarray(img)
img = img.convert('RGB')
img = transforms.ToTensor()(img)
img = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])(img)
return img.numpy(), img_meta["img_size"], img_meta["org_img_size"]
def __init__(self, opt=opt):
super(DataGenerater, self).__init__()
self.dir = opt.imgs_path
self.datalist = os.listdir(
self.dir) if opt.test == False else os.listdir(self.dir)[:100]
self.batch_size = opt.batch_size
img = Image.open(self.dir + self.datalist[0])
self.image_size = img.size
img.close()
self.transform = T.Compose([
T.Resize(opt.img_size),
T.CenterCrop(opt.img_size),
T.ToTensor(),
])
self.num_path_dict = {}
def load_train_test_datasets(dataset_root):
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
resize = transforms.Resize(256)
rcrop = transforms.RandomCrop((224, 224))
ccrop = transforms.CenterCrop((224, 224))
tot = transforms.ToTensor()
normalize = transforms.Normalize(mean, std)
train_transforms = transforms.Compose([resize, rcrop, tot, normalize])
test_transforms = transforms.Compose([resize, ccrop, tot, normalize])
train_set = DatasetFolder(osp.join(dataset_root, 'train'),
transform=train_transforms)
test_set = DatasetFolder(osp.join(dataset_root, 'test'),
transform=test_transforms)
return train_set, test_set
def __init__(self, model_path, use_cuda=True, use_static=False):
self.use_static = use_static
if not use_static:
self.net = torch.jit.load(model_path)
else:
place = paddle.CUDAPlace(0)
self.exe = paddle.static.Executor(place)
self.static_model = paddle.static.load_inference_model(
model_path, self.exe)
logger = logging.getLogger("root.tracker")
logger.info("Loading weights from {}... Done!".format(model_path))
# self.net.to(self.device)
self.size = (64, 128)
self.norm = transforms.Compose([
transforms.ToTensor(data_format='HWC'),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225],
data_format='HWC'),
])
def __init__(self, root_dir):
super(MXFaceDataset, self).__init__()
self.transform = transforms.Compose(
[
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
])
self.root_dir = root_dir
path_imgrec = os.path.join(root_dir, 'train.rec')
path_imgidx = os.path.join(root_dir, 'train.idx')
self.imgrec = recordio.MXIndexedRecordIO(path_imgidx, path_imgrec, 'r')
s = self.imgrec.read_idx(0)
header, _ = recordio.unpack(s)
if header.flag > 0:
self.header0 = (int(header.label[0]), int(header.label[1]))
self.imgidx = np.array(range(1, int(header.label[0])))
else:
self.imgidx = np.array(list(self.imgrec.keys))
def __init__(self, mode='train'):
super(HumanClasDataset, self).__init__()
self.data_path = "/home/aistudio/plane/bend/"
ps = os.listdir(osp.join(self.data_path, "p"))
ns = os.listdir(osp.join(self.data_path, "n"))
ps.sort()
ns.sort()
ps = [osp.join("p", n) for n in ps]
ns = [osp.join("n", n) for n in ns]
data = []
if mode == "train":
for idx in range(int(len(ps) * 0.8)):
data.append([ps[idx], 1])
for idx in range(int(len(ns) * 0.8)):
data.append([ns[idx], 0])
else:
for idx in range(int(len(ps) * 0.8), len(ps)):
data.append([ps[idx], 1])
for idx in range(int(len(ns) * 0.8), len(ns)):
data.append([ns[idx], 0])
self.data = data
self.transform = vt.Compose([vt.ToTensor()])
def main():
args = parse_args()
# 配置
config = Config(args.model_file, args.params_file)
config.disable_gpu()
config.switch_use_feed_fetch_ops(False)
config.switch_specify_input_names(True)
# 创建paddlePredictor
predictor = create_predictor(config)
# 获取输入
val_dataset = paddle.vision.datasets.MNIST(mode='test',
transform=transforms.ToTensor())
(image, label) = val_dataset[np.random.randint(10000)]
# fake_input = np.random.randn(1, 1, 28, 28).astype("float32")
# image = np.asndarray(image).astype("float32")
# print(image.shape)
image = image.numpy().reshape([1, 1, 28, 28])
# print(image.shape)
# print(fake_input.shape)
input_names = predictor.get_input_names()
input_handle = predictor.get_input_handle(input_names[0])
input_handle.reshape([1, 1, 28, 28])
input_handle.copy_from_cpu(image)
# 运行predictor
predictor.run()
# 获取输出
output_names = predictor.get_output_names()
output_handle = predictor.get_output_handle(output_names[0])
output = output_handle.copy_to_cpu()
print("True label: ", label.item())
print("Prediction: ", np.argmax(output))
tar.extract(name, "./")
model = paddle.jit.load("./paddle_resnet50/model")
######################################################################
# Load a test image
# ---------------------------------------------
# A single cat dominates the examples!
from PIL import Image
import paddle.vision.transforms as T
transforms = T.Compose([
T.Resize((256, 256)),
T.CenterCrop(224),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
img_url = "https://github.com/dmlc/mxnet.js/blob/main/data/cat.png?raw=true"
img_path = download_testdata(img_url, "cat.png", module="data")
img = Image.open(img_path).resize((224, 224))
img = transforms(img)
img = np.expand_dims(img, axis=0)
######################################################################
# Compile the model with relay
# ---------------------------------------------
target = "llvm"
def main(opt):
# torch.manual_seed(opt.seed)
# torch.backends.cudnn.benchmark = not opt.not_cuda_benchmark and not opt.test
paddle.seed(opt.seed)
print('Setting up data...')
Dataset = get_dataset(opt.dataset, opt.task)
f = open(opt.data_cfg)
data_config = json.load(f)
trainset_paths = data_config['train']
dataset_root = data_config['root']
f.close()
transforms = T.Compose([T.ToTensor()])
dataset = Dataset(opt,
dataset_root,
trainset_paths, (1088, 608),
augment=True,
transforms=transforms)
opt = opts().update_dataset_info_and_set_heads(opt, dataset)
print(opt)
logger = Logger(opt)
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
# opt.device = torch.device('cuda' if opt.gpus[0] >= 0 else 'cpu')
opt.device = paddle.get_device()
print('Creating model...')
model = create_model(opt.arch, opt.heads, opt.head_conv)
start_epoch = 0
# Get dataloader
# train_loader = torch.utils.data.DataLoader(
# dataset,
# batch_size=opt.batch_size,
# shuffle=True,
# num_workers=opt.num_workers,
# pin_memory=True,
# drop_last=True
# )
train_loader = DataLoader(dataset,
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.num_workers,
use_shared_memory=False,
drop_last=True)
print('Starting training...')
Trainer = train_factory[opt.task]
# optimizer = torch.optim.Adam(model.parameters(), opt.lr)
# optimizer = paddle.optimizer.Adam(learning_rate=opt.lr, parameters=model.parameters()) # 这句代码的作用纯粹是为了传个参数，
# trainer = Trainer(opt, model, optimizer)
trainer = Trainer(opt, model)
optimizer = trainer.optimizer # 见base_trainer.py
id_classifier = trainer.loss.classifier # 见base_trainer.py
trainer.set_device(opt.gpus, opt.chunk_sizes, opt.device)
if 'fairmot_hrnet_w18' in opt.load_model:
model = load_model(model, opt.load_model)
elif opt.load_model != '':
model, optimizer, start_epoch, id_classifier = load_model(
model, opt.load_model, trainer.optimizer, trainer.loss.classifier,
opt.resume, opt.lr, opt.lr_step)
for epoch in range(start_epoch + 1, opt.num_epochs + 1):
mark = epoch if opt.save_all else 'last'
log_dict_train, _ = trainer.train(epoch, train_loader)
logger.write('epoch: {} |'.format(epoch))
for k, v in log_dict_train.items():
logger.scalar_summary('train_{}'.format(k), v, epoch)
logger.write('{} {:8f} | '.format(k, v))
if opt.val_intervals > 0 and epoch % opt.val_intervals == 0:
save_model(
os.path.join(opt.save_dir, 'model_{}.pdparams'.format(mark)),
epoch, model, optimizer, id_classifier)
else:
save_model(os.path.join(opt.save_dir, 'model_last.pdparams'),
epoch, model, optimizer, id_classifier)
logger.write('\n')
if epoch in opt.lr_step:
save_model(
os.path.join(opt.save_dir, 'model_{}.pdparams'.format(epoch)),
epoch, model, optimizer, id_classifier)
lr = opt.lr * (0.1**(opt.lr_step.index(epoch) + 1))
print('Drop LR to', lr)
# for param_group in optimizer.param_groups:
# param_group['lr'] = lr
optimizer.set_lr(lr)
if epoch % 5 == 0 or epoch >= 25:
save_model(
os.path.join(opt.save_dir, 'model_{}.pdparams'.format(epoch)),
epoch, model, optimizer, id_classifier)
logger.close()
def __getitem__(self, index):
img_path = synth_train_data_dir + self.img_paths[index][0]
img = get_img(img_path, read_type=self.read_type)
bboxes, words = get_ann(img, self.gts, self.texts, index)
if bboxes.shape[0] > self.max_word_num:
bboxes = bboxes[:self.max_word_num]
words = words[:self.max_word_num]
if self.is_transform:
img = random_scale(img, self.short_size)
gt_instance = np.zeros(img.shape[0:2], dtype='uint8')
training_mask = np.ones(img.shape[0:2], dtype='uint8')
if bboxes.shape[0] > 0:
bboxes = np.reshape(bboxes * ([img.shape[1], img.shape[0]] * 4),
(bboxes.shape[0], -1, 2)).astype('int32')
for i in range(bboxes.shape[0]):
cv2.drawContours(gt_instance, [bboxes[i]], -1, i + 1, -1)
if words[i] == '###':
cv2.drawContours(training_mask, [bboxes[i]], -1, 0, -1)
gt_kernels = []
for i in range(1, self.kernel_num):
rate = 1.0 - (1.0 - self.min_scale) / (self.kernel_num - 1) * i
gt_kernel = np.zeros(img.shape[0:2], dtype='uint8')
kernel_bboxes = shrink(bboxes, rate)
for i in range(len(bboxes)):
cv2.drawContours(gt_kernel, [kernel_bboxes[i].astype(int)], -1,
1, -1)
gt_kernels.append(gt_kernel)
if self.is_transform:
imgs = [img, gt_instance, training_mask]
imgs.extend(gt_kernels)
imgs = random_horizontal_flip(imgs)
imgs = random_rotate(imgs)
imgs = random_crop_padding(imgs, self.img_size)
img, gt_instance, training_mask, gt_kernels = imgs[0], imgs[
1], imgs[2], imgs[3:]
gt_text = gt_instance.copy()
gt_text[gt_text > 0] = 1
gt_kernels = np.array(gt_kernels)
max_instance = np.max(gt_instance)
gt_bboxes = np.zeros((self.max_word_num, 4), dtype=np.int32)
for i in range(1, max_instance + 1):
ind = gt_instance == i
if np.sum(ind) == 0:
continue
points = np.array(np.where(ind)).transpose((1, 0))
tl = np.min(points, axis=0)
br = np.max(points, axis=0) + 1
gt_bboxes[i] = (tl[0], tl[1], br[0], br[1])
img = Image.fromarray(img)
img = img.convert('RGB')
if self.is_transform:
img = transforms.ColorJitter(brightness=32.0 / 255,
saturation=0.5)(img)
img = transforms.ToTensor()(img)
img = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])(img)
gt_text = paddle.to_tensor(gt_text, dtype="int64")
gt_kernels = paddle.to_tensor(gt_kernels, dtype="int64")
training_mask = paddle.to_tensor(training_mask, dtype="int64")
data = dict(
imgs=img,
gt_texts=gt_text,
gt_kernels=gt_kernels,
training_masks=training_mask,
)
return img.numpy(), gt_text.numpy(), gt_kernels.numpy(
), training_mask.numpy()
def predict(path, model, cfg, out_path):
if not os.path.exists(out_path):
os.makedirs(out_path)
model.eval()
rf = ResultFormat(cfg.data.test.type, cfg.test_cfg.result_path)
if cfg.report_speed:
speed_meters = dict(backbone_time=AverageMeter(500),
neck_time=AverageMeter(500),
det_head_time=AverageMeter(500),
det_pse_time=AverageMeter(500),
rec_time=AverageMeter(500),
total_time=AverageMeter(500))
def get_img(img_path, read_type='pil'):
try:
if read_type == 'cv2':
img = cv2.imread(img_path)
img = img[:, :, [2, 1, 0]]
elif read_type == 'pil':
img = np.array(Image.open(img_path))
except Exception as e:
print('Cannot read image: %s.' % img_path)
raise
return img
def scale_aligned_short(img, short_size=736):
h, w = img.shape[0:2]
scale = short_size * 1.0 / min(h, w)
h = int(h * scale + 0.5)
w = int(w * scale + 0.5)
if h % 32 != 0:
h = h + (32 - h % 32)
if w % 32 != 0:
w = w + (32 - w % 32)
img = cv2.resize(img, dsize=(w, h))
return img
imgs_list = os.listdir(path)
data_lists = []
for img_path in imgs_list:
img = get_img(osp.join(path, img_path))
img_meta = dict(org_img_size=np.array(img.shape[:2]))
img = scale_aligned_short(img, int(cfg.data.test.short_size))
img_meta.update(dict(img_size=np.array(img.shape[:2])))
img = Image.fromarray(img)
img = img.convert('RGB')
img = transforms.ToTensor()(img)
img = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])(img)
img = img.numpy()
img = np.expand_dims(img, axis=0)
img = paddle.to_tensor(img)
img_meta["img_size"] = paddle.to_tensor(
np.expand_dims(img_meta["img_size"], axis=0))
img_meta["org_img_size"] = paddle.to_tensor(
np.expand_dims(img_meta["org_img_size"], axis=0))
data_lists.append((img, img_meta["img_size"], img_meta["org_img_size"],
osp.join(path, img_path)))
for idx, data in enumerate(data_lists):
img_meta = {}
img_meta["img_size"] = data[1]
img_meta["org_img_size"] = data[2]
img_path = data[3]
data_dict = dict(imgs=data[0], img_metas=img_meta)
print('Testing %d/%d' % (idx, len(data_lists)))
sys.stdout.flush()
# prepare input
data_dict['imgs'] = data_dict['imgs']
data_dict.update(dict(cfg=cfg))
# forward
with paddle.no_grad():
outputs = model(**data_dict)
if cfg.report_speed:
report_speed(outputs, speed_meters)
data_type = cfg.data.train.type
if data_type == "PSENET_IC15" or data_type == "PSENET_IC17":
save_img = cv2.imread(img_path)
for bbox in outputs["bboxes"]:
cv2.rectangle(save_img, (bbox[2], bbox[3]), (bbox[6], bbox[7]),
(0, 0, 255), 2)
save_jpg = img_path.split("/")[-1]
save_img_path = osp.join(out_path, save_jpg)
cv2.imwrite(save_img_path, save_img)
elif data_type == "PSENET_TT":
save_img = cv2.imread(img_path)
for bbox in outputs["bboxes"]:
xs = []
ys = []
i = 0
for point in bbox:
if i % 2 == 0:
xs.append(point)
else:
ys.append(point)
i = i + 1
for idx, x in enumerate(xs):
if idx < len(xs) - 1:
cv2.line(save_img, (x, ys[idx]),
(xs[idx + 1], ys[idx + 1]), (0, 0, 255), 2)
else:
cv2.line(save_img, (x, ys[idx]), (xs[0], ys[0]),
(0, 0, 255), 2)
save_jpg = img_path.split("/")[-1]
save_img_path = osp.join(out_path, save_jpg)
cv2.imwrite(save_img_path, save_img)
logger.info("=" * 60)
logger.info("Overall Configurations:")
for cfg_, value in cfg.items():
logger.info(cfg_ + ":" + str(value))
logger.info("=" * 60)
fleet.init(is_collective=True)
train_transform = transforms.Compose([
# refer to https://pytorch.org/docs/stable/torchvision/transforms.html for more build-in online data augmentation
transforms.Resize(
[int(128 * INPUT_SIZE[0] / 112),
int(128 * INPUT_SIZE[0] / 112)]), # smaller side resized
transforms.RandomCrop([INPUT_SIZE[0], INPUT_SIZE[1]]),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=RGB_MEAN, std=RGB_STD),
])
logger.info('loading data form file:{}'.format(DATA_ROOT))
train_dataset = LFWDataset(os.path.join(DATA_ROOT), train_transform)
num_classes = train_dataset.num_classes
train_loader = paddle.io.DataLoader(train_dataset,
places=[paddle.CPUPlace()],
batch_size=BATCH_SIZE,
shuffle=True,
drop_last=DROP_LAST,
num_workers=NUM_WORKERS)
NUM_CLASS = train_dataset.num_classes
logger.info("Number of Training Classes: {}".format(NUM_CLASS))
# lfw, cfp_ff, cfp_fp, agedb, calfw, cplfw, vgg2_fp, lfw_issame, cfp_ff_issame, cfp_fp_issame, agedb_issame, calfw_issame, cplfw_issame, vgg2_fp_issame = get_val_data(
import paddle
import paddle.vision.transforms as transforms
# will segment fault
num_workers = 0
# OK
# num_workers = 1
trainset = paddle.vision.datasets.MNIST(mode='test',
transform=transforms.ToTensor())
trainloader = paddle.io.DataLoader(trainset,
batch_size=32,
num_workers=num_workers,
shuffle=True)
for epoch_id in range(3):
print("start iter")
for batch_idx, data in enumerate(trainloader):
print("epoch {}, batch {}".format(epoch_id, batch_idx))
return len(self.segment)
def __getitem__(self, idx):
data = self.segment[idx]
with data.open() as fp:
image_tensor = self.transform(Image.open(fp))
return image_tensor, self.category_to_index[
data.label.classification.category]
# """"""
"""Build a dataloader and run it"""
ACCESS_KEY = "<YOUR_ACCESSKEY>"
to_tensor = transforms.ToTensor()
normalization = transforms.Normalize(mean=[0.485], std=[0.229])
my_transforms = transforms.Compose([to_tensor, normalization])
train_segment = DogsVsCatsSegment(GAS(ACCESS_KEY),
segment_name="train",
transform=my_transforms)
train_dataloader = DataLoader(train_segment,
batch_size=4,
shuffle=True,
num_workers=0)
for index, (image, label) in enumerate(train_dataloader):
print(f"{index}: {label}")
""""""
