ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (6,) + inhomogeneous part. #589
Description
(yolo) E:\download\anaconda\envs\ssd.pytorch-master>python train.py
E:\download\anaconda\envs\ssd.pytorch-master\ssd.py:34: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
self.priors = Variable(self.priorbox.forward(), volatile=True)
Loading base network...
Initializing weights...
E:\download\anaconda\envs\ssd.pytorch-master\train.py:218: UserWarning: nn.init.xavier_uniform is now deprecated in favor of nn.init.xavier_uniform_.
init.xavier_uniform(param)
Loading the dataset...
Training SSD on: VOC0712
Using the specified args:
Namespace(dataset='VOC', dataset_root='E:/download/anaconda/envs/ssd.pytorch-master/data/VOCdevkit/', basenet='vgg16_reducedfc.pth', batch_size=32, resume=None, start_iter=0, num_workers=4, cuda=True, lr=0.001, momentum=0.9, weight_decay=0.0005, gamma=0.1, visdom=False, save_folder='weights/')
Traceback (most recent call last):
File "E:\download\anaconda\envs\ssd.pytorch-master\train.py", line 259, in
train()
File "E:\download\anaconda\envs\ssd.pytorch-master\train.py", line 169, in train
images, targets = next(batch_iterator)
File "E:\download\anaconda\envs\yolo\lib\site-packages\torch\utils\data\dataloader.py", line 633, in next
data = self._next_data()
File "E:\download\anaconda\envs\yolo\lib\site-packages\torch\utils\data\dataloader.py", line 1345, in _next_data
return self._process_data(data)
File "E:\download\anaconda\envs\yolo\lib\site-packages\torch\utils\data\dataloader.py", line 1371, in _process_data
data.reraise()
File "E:\download\anaconda\envs\yolo\lib\site-packages\torch_utils.py", line 644, in reraise
raise exception
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "E:\download\anaconda\envs\yolo\lib\site-packages\torch\utils\data_utils\worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "E:\download\anaconda\envs\yolo\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\download\anaconda\envs\yolo\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\download\anaconda\envs\ssd.pytorch-master\data\voc0712.py", line 115, in getitem
im, gt, h, w = self.pull_item(index)
File "E:\download\anaconda\envs\ssd.pytorch-master\data\voc0712.py", line 134, in pull_item
img, boxes, labels = self.transform(img, target[:, :4], target[:, 4])
File "E:\download\anaconda\envs\ssd.pytorch-master\utils\augmentations.py", line 417, in call
return self.augment(img, boxes, labels)
File "E:\download\anaconda\envs\ssd.pytorch-master\utils\augmentations.py", line 52, in call
img, boxes, labels = t(img, boxes, labels)
File "E:\download\anaconda\envs\ssd.pytorch-master\utils\augmentations.py", line 238, in call
mode = random.choice(self.sample_options)
File "mtrand.pyx", line 920, in numpy.random.mtrand.RandomState.choice
ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (6,) + inhomogeneous part.
for all the code ,I change three place
one and two is the way of file
COCO_ROOT = osp.join('E:/download/anaconda/envs/ssd.pytorch-master/data/coco/') in coco.py
VOC_ROOT = osp.join("E:/download/anaconda/envs/ssd.pytorch-master/data/VOCdevkit/") in VOC0721.py
three is in train.py for the error (RuntimeError: Expected a 'cuda' device type for generator but found 'cpu')
# data_loader = data.DataLoader(dataset, args.batch_size,
# num_workers=args.num_workers,
# shuffle=True, collate_fn=detection_collate,
# pin_memory=True)
data_loader = data.DataLoader(dataset, args.batch_size,
num_workers=args.num_workers,
shuffle=True, collate_fn=detection_collate,
pin_memory=True, generator=torch.Generator(device='cuda'))
that's all.I think I didn't change any parameter.