I am training an object detection model on my Dataset using Faster RCNN and resnet50 with pre-trained weights. I am primarily following the following link while implementing it, the only difference is that instead of segmentation, I am performing object detection.
However, a few steps after I start training, I get the following error
Epoch: [0] [ 0/4181] eta: 20:35:42 lr: 0.000010 loss: 3.4489 (3.4489) loss_classifier: 2.0232 (2.0232) loss_box_reg: 0.0210 (0.0210) loss_objectness: 1.0478 (1.0478) loss_rpn_box_reg: 0.3568 (0.3568) time: 17.7333 data: 6.1786 max mem: 2559
Traceback (most recent call last):
File "train.py", line 156, in <module>
train_one_epoch(model, optimizer, data_loader_train, device, epoch, print_freq=1)
File "/media/charan/Data/Charan_Data/FLIR_RTFNet/custom/engine.py", line 36, in train_one_epoch
loss_dict = model(images, targets)
File "/home/charan/anaconda3/envs/flir_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/home/charan/anaconda3/envs/flir_env/lib/python3.7/site-packages/torchvision/models/detection/generalized_rcnn.py", line 47, in forward
images, targets = self.transform(images, targets)
File "/home/charan/anaconda3/envs/flir_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/home/charan/anaconda3/envs/flir_env/lib/python3.7/site-packages/torchvision/models/detection/transform.py", line 41, in forward
image, target = self.resize(image, target)
File "/home/charan/anaconda3/envs/flir_env/lib/python3.7/site-packages/torchvision/models/detection/transform.py", line 76, in resize
bbox = resize_boxes(bbox, (h, w), image.shape[-2:])
File "/home/charan/anaconda3/envs/flir_env/lib/python3.7/site-packages/torchvision/models/detection/transform.py", line 137, in resize_boxes
xmin, ymin, xmax, ymax = boxes.unbind(1)
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)
My code to load the data is as follows
class CustomDataset(torch.utils.data.Dataset):
def __init__(self, root_dir,transform=None):
self.root = root_dir
self.rgb_imgs = list(sorted(os.listdir(os.path.join(root_dir, "rgb/"))))
self.annotations = list(sorted(os.listdir(os.path.join(root_dir, "annotations/"))))
self._classes = ('__background__', # always index 0
'car','person','bicycle','dog','other')
self._class_to_ind = {'car':'3', 'person':'1', 'bicycle':'2', 'dog':'18','other':'91'}
self.rtf_net = RTFNet(6)
def __len__(self):
return len(self.rgb_imgs)
def __getitem__(self, idx):
self.num_classes = 6
img_rgb_path = os.path.join(self.root, "rgb/", self.rgb_imgs[idx])
img = Image.open(img_rgb_path)
img = np.array(img)
img = img.transpose((2, 0, 1))
img = torch.from_numpy(img)
filename = os.path.join(self.root,'annotations',self.annotations[idx])
tree = ET.parse(filename)
objs = tree.findall('object')
num_objs = len(objs)
boxes = np.zeros((num_objs, 4), dtype=np.uint16)
labels = np.zeros((num_objs), dtype=np.float32)
seg_areas = np.zeros((num_objs), dtype=np.float32)
boxes = []
for ix, obj in enumerate(objs):
bbox = obj.find('bndbox')
x1 = float(bbox.find('xmin').text)
y1 = float(bbox.find('ymin').text)
x2 = float(bbox.find('xmax').text)
y2 = float(bbox.find('ymax').text)
cls = self._class_to_ind[obj.find('name').text.lower().strip()]
boxes.append([x1, y1, x2, y2])
labels[ix] = cls
seg_areas[ix] = (x2 - x1 + 1) * (y2 - y1 + 1)
boxes = torch.as_tensor(boxes, dtype=torch.float32)
seg_areas = torch.as_tensor(seg_areas, dtype=torch.float32)
labels = torch.as_tensor(labels, dtype=torch.float32)
target = {'boxes': boxes,
'labels': labels,
'seg_areas': seg_areas,
}
return img,target
The bounding boxes are in PASCAL VOC format(xmin,ymin,xmax and ymax)
My code to train the data is as follows
num_classes = 6
model = fasterrcnn_resnet50_fpn(pretrained=True)
in_features = model.roi_heads.box_predictor.cls_score.in_features
model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)
dataset_train = CustomDataset('images/train/')
dataset_val = CustomDataset('images/val/')
print('Loading data')
data_loader_train = torch.utils.data.DataLoader(
dataset_train, batch_size=2, shuffle=True,collate_fn=utils.collate_fn)
data_loader_test = torch.utils.data.DataLoader(
dataset_val, batch_size=2, shuffle=False,collate_fn=utils.collate_fn)
print('Done loading')
# device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
device = torch.device('cuda')
model.to(device)
# construct an optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params, lr=0.005,
momentum=0.9, weight_decay=0.0005)
# and a learning rate scheduler which decreases the learning rate by
# 10x every 3 epochs
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=3,
gamma=0.1)
num_epochs = 10
for epoch in range(num_epochs):
# train for one epoch, printing every 10 iterations
train_one_epoch(model, optimizer, data_loader_train, device, epoch, print_freq=1)
# update the learning rate
lr_scheduler.step()
# evaluate on the test dataset
evaluate(model, data_loader_val, device=device)
The train_one_epoch
function is at the following link
Can someone please help me out.