Python Anno_xml2list примеры использования

Пример #1

print("trainlist: ", len(train_img_list))
print("vallist: ", len(val_img_list))

# make Dataset
voc_classes = [
    'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat',
    'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike', 'person',
    'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor'
]

input_size = 300 * scale  # 画像のinputサイズを300×300にする

## DatasetTransformを適応
transform = DatasetTransform(input_size)
transform_anno = Anno_xml2list(voc_classes)

# Dataloaderに入れるデータセットファイル。
# ゲットで叩くと画像とGTを前処理して出力してくれる。
train_dataset = VOCDataset(train_img_list,
                           train_anno_list,
                           phase="train",
                           transform=transform,
                           transform_anno=transform_anno)
val_dataset = VOCDataset(val_img_list,
                         val_anno_list,
                         phase="val",
                         transform=DatasetTransform(input_size, color_mean),
                         transform_anno=Anno_xml2list(voc_classes))

batch_size = 32

Пример #2

Файл: train_BlazeFace.py Проект: xiefeiwhu/BlazeFace_Person.pytorch

vocpath = "../VOCdevkit/VOC2012"
train_img_list2, train_anno_list2, _, _ = make_datapath_list(vocpath, cls="person", VOC2012=True)

train_img_list.extend(train_img_list2)
train_anno_list.extend(train_anno_list2)

# make Dataset
voc_classes = ['person']
color_mean = (104, 117, 123)  # (BGR)の色の平均値

print("trainlist: ", len(train_img_list))
print("vallist: ", len(val_img_list))

## DatasetTransformを適応
transform = DatasetTransform(input_size, color_mean)
transform_anno = Anno_xml2list(voc_classes)

train_dataset = VOCDataset(train_img_list, train_anno_list, phase = "train", transform=transform, transform_anno = transform_anno)
val_dataset = VOCDataset(val_img_list, val_anno_list, phase="val", transform=DatasetTransform(
    input_size, color_mean), transform_anno=Anno_xml2list(voc_classes))

train_dataloader = data.DataLoader(
    train_dataset, batch_size=batch_size, shuffle=True, collate_fn=od_collate_fn, num_workers=8)

val_dataloader = data.DataLoader(
    val_dataset, batch_size=batch_size, shuffle=False, collate_fn=od_collate_fn, num_workers=8)

dataloaders_dict = {"train": train_dataloader, "val": val_dataloader}


# In[4]:

Пример #3

val_img_list[0]

# In[6]:

class_names = [
    'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat',
    'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike', 'person',
    'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor'
]
color_mean = (104, 117, 123)  # (BGR)???F???????l
input_size = 300  # ??????input?T?C?Y??300?~300??????

## DatasetTransform???K??
transform = DatasetTransform(input_size, color_mean)
transform_anno = Anno_xml2list(class_names)

# In[7]:

val_dataset = VOCDataset(val_img_list,
                         val_anno_list,
                         phase="val",
                         transform=DatasetTransform(input_size, color_mean),
                         transform_anno=Anno_xml2list(class_names))

# In[8]:

val_dataloader = data.DataLoader(val_dataset,
                                 batch_size=1,
                                 shuffle=False,
                                 collate_fn=od_collate_fn,