how can I modify Dataset class to make the mask RCNN work with multiple objects?
I am currently working on instance segmentation. I follow these two tutorials:
However, these two tutorials work perfectly with one class like person + background. But in my case, I have two classes like a person and car + background. I didn't find any resources about making the Mask RCNN work with multiple objects.
Notice that:
I am using PyTorch ( torchvision ), torch==1.10.0+cu111 torchvision==0.11.0+cu111 torchaudio==0.10.0
I am using a Pascal VOC annotation
i used segmentation class (not the XML file) + the images
and this is my dataset class
class PennFudanDataset(torch.utils.data.Dataset):
def __init__(self, root, transforms=None):
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, "img"))))
self.masks = list(sorted(os.listdir(os.path.join(root, "imgMask"))))
def __getitem__(self, idx):
# load images ad masks
img_path = os.path.join(self.root, "img", self.imgs[idx])
mask_path = os.path.join(self.root, "imgMask", 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)
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])
boxes = torch.as_tensor(boxes, dtype=torch.float32)
# there is only one class
labels = torch.ones((num_objs,), dtype=torch.int64)
masks = torch.as_tensor(masks, dtype=torch.uint8)
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["masks"] = masks
target["image_id"] = image_id
target["area"] = area
target["iscrowd"] = iscrowd
if self.transforms is not None:
img, target = self.transforms(img, target)
return img, target
def __len__(self):
return len(self.imgs)
anyone can help me?
How many English words
do you know?
do you know?
Test your English vocabulary size, and measure
how many words do you know
Online Test
how many words do you know
Powered by Examplum
