# extend with VOC2012
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}
train_anno_list.extend(train_anno_list2)
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))