how to change the input picture's dimension

[msha096]

Hi, I am trying to use my own dataset and the image is 1024*2048. I changed the 'input size' of 'db', in config/CenterNet104.json. But I got the following errors:

Traceback (most recent call last):
File "train.py", line 207, in
train(training_dbs, validation_db, args.start_iter)
File "train.py", line 139, in train
training_loss, focal_loss, pull_loss, push_loss, regr_loss = nnet.train(**training)
File "/home/mingzhi/Downloads/CenterNet-master/nnet/py_factory.py", line 82, in train
loss_kp = self.network(xs, ys)
File "/home/mingzhi/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/mingzhi/Downloads/CenterNet-master/models/py_utils/data_parallel.py", line 68, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/mingzhi/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/mingzhi/Downloads/CenterNet-master/nnet/py_factory.py", line 21, in forward
loss_kp = self.loss(preds, ys, **kwargs)
File "/home/mingzhi/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/mingzhi/Downloads/CenterNet-master/models/py_utils/kp.py", line 339, in forward
pull, push = self.ae_loss(tl_tag, br_tag, gt_mask)
File "/home/mingzhi/Downloads/CenterNet-master/models/py_utils/kp_utils.py", line 224, in _ae_loss
dist = tag_mean.unsqueeze(1) - tag_mean.unsqueeze(2)
RuntimeError: Dimension out of range (expected to be in range of [-2, 1], but got 2)

[Duankaiwen]

@msha096 Can I see your full log?

[msha096]

@msha096 Can I see your full log?

Yes here it is. If I change to [1024,2048], it will be out of my cuda's capability.So I changed to 512,1024.

(CenterNet) ➜ CenterNet-master python train.py CenterNet-104
loading all datasets...
using 4 threads
loading from cache file: cache/coco_train.pkl
loading annotations into memory...
annotations_file ./data/coco/annotations/instances_train.json
Done (t=0.05s)
creating index...
index created!
loading from cache file: cache/coco_train.pkl
loading annotations into memory...
annotations_file ./data/coco/annotations/instances_train.json
Done (t=0.06s)
creating index...
index created!
loading from cache file: cache/coco_train.pkl
loading annotations into memory...
annotations_file ./data/coco/annotations/instances_train.json
Done (t=0.06s)
creating index...
index created!
loading from cache file: cache/coco_train.pkl
loading annotations into memory...
annotations_file ./data/coco/annotations/instances_train.json
Done (t=0.04s)
creating index...
index created!
loading from cache file: cache/coco_val.pkl
loading annotations into memory...
annotations_file ./data/coco/annotations/instances_val.json
Done (t=0.01s)
creating index...
index created!
system config...
{'batch_size': 1,
'cache_dir': 'cache',
'chunk_sizes': [1],
'config_dir': 'config',
'data_dir': './data',
'data_rng': <mtrand.RandomState object at 0x7feb675e3510>,
'dataset': 'MSCOCO',
'decay_rate': 10,
'display': 5,
'learning_rate': 0.00025,
'max_iter': 480000,
'nnet_rng': <mtrand.RandomState object at 0x7feb675e3558>,
'opt_algo': 'adam',
'prefetch_size': 6,
'pretrain': None,
'result_dir': 'results',
'sampling_function': 'kp_detection',
'snapshot': 5000,
'snapshot_name': 'CenterNet-104',
'stepsize': 450000,
'test_split': 'testdev',
'train_split': 'trainval',
'val_iter': 500,
'val_split': 'minival',
'weight_decay': False,
'weight_decay_rate': 1e-05,
'weight_decay_type': 'l2'}
db config...
{'ae_threshold': 0.5,
'border': 128,
'categories': 80,
'data_aug': True,
'gaussian_bump': True,
'gaussian_iou': 0.7,
'gaussian_radius': -1,
'input_size': [512, 1024],
'kp_categories': 1,
'lighting': True,
'max_per_image': 100,
'merge_bbox': False,
'nms_algorithm': 'exp_soft_nms',
'nms_kernel': 3,
'nms_threshold': 0.5,
'output_sizes': [[128, 256]],
'rand_color': True,
'rand_crop': True,
'rand_pushes': False,
'rand_samples': False,
'rand_scale_max': 1.4,
'rand_scale_min': 0.6,
'rand_scale_step': 0.1,
'rand_scales': array([0.6, 0.7, 0.8, 0.9, 1. , 1.1, 1.2, 1.3]),
'special_crop': False,
'test_scales': [1],
'top_k': 70,
'weight_exp': 8}
len of db: 1126
start prefetching data...
shuffling indices...
start prefetching data...
shuffling indices...
start prefetching data...
shuffling indices...
start prefetching data...
shuffling indices...
building model...
module_file: models.CenterNet-104
start prefetching data...
shuffling indices...
total parameters: 210062960
setting learning rate to: 0.00025
training start...
0%| | 0/480000 [00:00<?, ?it/s]/home/mingzhi/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/nn/modules/upsampling.py:122: UserWarning: nn.Upsampling is deprecated. Use nn.functional.interpolate instead.
warnings.warn("nn.Upsampling is deprecated. Use nn.functional.interpolate instead.")

Traceback (most recent call last):
File "train.py", line 208, in
train(training_dbs, validation_db, args.start_iter)
File "train.py", line 139, in train
training_loss, focal_loss, pull_loss, push_loss, regr_loss = nnet.train(**training)
File "/home/mingzhi/Downloads/CenterNet-master/nnet/py_factory.py", line 82, in train
loss_kp = self.network(xs, ys)
File "/home/mingzhi/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/mingzhi/Downloads/CenterNet-master/models/py_utils/data_parallel.py", line 68, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/mingzhi/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/mingzhi/Downloads/CenterNet-master/nnet/py_factory.py", line 21, in forward
loss_kp = self.loss(preds, ys, **kwargs)
File "/home/mingzhi/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/mingzhi/Downloads/CenterNet-master/models/py_utils/kp.py", line 339, in forward
pull, push = self.ae_loss(tl_tag, br_tag, gt_mask)
File "/home/mingzhi/Downloads/CenterNet-master/models/py_utils/kp_utils.py", line 224, in _ae_loss
dist = tag_mean.unsqueeze(1) - tag_mean.unsqueeze(2)
RuntimeError: Dimension out of range (expected to be in range of [-2, 1], but got 2)

[Duankaiwen]

@msha096 Add these codes above the
dist = tag_mean.unsqueeze(1) - tag_mean.unsqueeze(2)
in models/py_utils/kp_utils.py:

if len(tag_mean.size()) < 2:

      tag_mean = tag_mean.unsqueeze(0)`  

[z-huabao]

@Duankaiwen why not update the code on repos