如何在数据集上训练更快的rcnn，包括pytorch中的负数据

Question

我正在尝试训练 torchvision Faster R-CNN 模型以对我的自定义数据进行对象检测。我在torchvision对象检测微调tutorial中使用了代码。但收到此错误：

Expected target boxes to be a tensor of shape [N, 4], got torch.Size([0])

这与我的自定义数据集中的负数据（空训练图像/无边界框）有关。我们如何更改下面的Dataset class 以在包含负数据的数据集上训练更快的rcnn？

class MyCustomDataset(Dataset):

    def __init__(self, root, transforms):
        self.root = root
        self.transforms = transforms
        # load all image files, sorting them to
        # ensure that they are aligned
        self.imgs = list(sorted(os.listdir(os.path.join(root, "PNGImages"))))
        self.masks = list(sorted(os.listdir(os.path.join(root, "PedMasks"))))

    def __len__(self):
        return len(self.imgs)

    def __getitem__(self, idx):
        # load images ad masks
        img_path = os.path.join(self.root, "PNGImages", self.imgs[idx])
        mask_path = os.path.join(self.root, "PedMasks", self.masks[idx])
        img = Image.open(img_path).convert("RGB")
        # note that we haven't converted the mask to RGB,
        # because each color corresponds to a different instance
        # with 0 being background
        mask = Image.open(mask_path)
        # convert the PIL Image into a numpy array
        mask = np.array(mask)
        # instances are encoded as different colors
        obj_ids = np.unique(mask)
        # first id is the background, so remove it
        obj_ids = obj_ids[1:]

        # split the color-encoded mask into a set of binary masks
        masks = mask == obj_ids[:, None, None]

        # get bounding box coordinates for each mask
        num_objs = len(obj_ids)
        
        boxes = []
        for i in range(num_objs):
            pos = np.where(masks[i])
            xmin = np.min(pos[1])
            xmax = np.max(pos[1])
            ymin = np.min(pos[0])
            ymax = np.max(pos[0])
            boxes.append([xmin, ymin, xmax, ymax])

        # convert everything into a torch.Tensor
        boxes = torch.as_tensor(boxes, dtype=torch.float32)      
        # there is only one class  
        labels = torch.ones((num_objs,), dtype=torch.int64)
        image_id = torch.tensor([idx])
        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])
        # suppose all instances are not crowd
        iscrowd = torch.zeros((num_objs,), dtype=torch.int64)

        target = {}
        target["boxes"] = boxes
        target["labels"] = labels
        target["image_id"] =  torch.tensor([idx])
        target["area"] = area
        target["iscrowd"] = iscrowd

        return img, target 

Answer 1

我们需要对数据集类进行两项更改。

1- 空盒子的输入为：

if num_objs == 0:
    boxes = torch.zeros((0, 4), dtype=torch.float32)
else:
    boxes = torch.as_tensor(boxes, dtype=torch.float32)

2- 将area=0分配给空边界框的情况，更改用于计算面积的代码，使其成为torch tensor：

area = 0
for i in range(num_objs):
    pos = np.where(masks[i])
    xmin = np.min(pos[1])
    xmax = np.max(pos[1])
    ymin = np.min(pos[0])
    ymax = np.max(pos[0])
    area += (xmax-xmin)*(ymax-ymin)
area = torch.as_tensor(area, dtype=torch.float32)

我们将把第 2 步合并到现有的 for 循环中。

因此，修改后的数据集类将如下所示：

class MyCustomDataset(Dataset):

    def __init__(self, root, transforms):
        self.root = root
        self.transforms = transforms
        # load all image files, sorting them to
        # ensure that they are aligned
        self.imgs = list(sorted(os.listdir(os.path.join(root, "PNGImages"))))
        self.masks = list(sorted(os.listdir(os.path.join(root, "PedMasks"))))

    def __len__(self):
        return len(self.imgs)

    def __getitem__(self, idx):
        # load images ad masks
        img_path = os.path.join(self.root, "PNGImages", self.imgs[idx])
        mask_path = os.path.join(self.root, "PedMasks", self.masks[idx])
        img = Image.open(img_path).convert("RGB")
        # note that we haven't converted the mask to RGB,
        # because each color corresponds to a different instance
        # with 0 being background
        mask = Image.open(mask_path)
        # convert the PIL Image into a numpy array
        mask = np.array(mask)
        # instances are encoded as different colors
        obj_ids = np.unique(mask)
        # first id is the background, so remove it
        obj_ids = obj_ids[1:]

        # split the color-encoded mask into a set of binary masks
        masks = mask == obj_ids[:, None, None]

        # get bounding box coordinates for each mask
        num_objs = len(obj_ids)
        
        boxes = []
        area = 0 
        for i in range(num_objs):
            pos = np.where(masks[i])
            xmin = np.min(pos[1])
            xmax = np.max(pos[1])
            ymin = np.min(pos[0])
            ymax = np.max(pos[0])
            boxes.append([xmin, ymin, xmax, ymax])
            area += (xmax-xmin)*(ymax-ymin)
        area = torch.as_tensor(area, dtype=torch.float32)

        # Handle empty bounding boxes
        if num_objs == 0:
            boxes = torch.zeros((0, 4), dtype=torch.float32)
        else:
            boxes = torch.as_tensor(boxes, dtype=torch.float32)   

        # there is only one class  
        labels = torch.ones((num_objs,), dtype=torch.int64)
        image_id = torch.tensor([idx])

        #area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])

        # suppose all instances are not crowd
        iscrowd = torch.zeros((num_objs,), dtype=torch.int64)

        target = {}
        target["boxes"] = boxes
        target["labels"] = labels
        target["image_id"] =  torch.tensor([idx])
        target["area"] = area
        target["iscrowd"] = iscrowd

        return img, target