Hi,I have a question to ask you.When I do the viusalization process of running Sparse-to-dense hypercolumn matching. A error occurs.Could you tell me how to solved it?
python run.py --dataset robotcar --mode sparse_to_dense --log_images
Found 1 GPUs to use.
Found 6954 reference images.
Found 3978 query images.
Loading poses from /media/hdd/zhou/datasets/images/all.nvm
import datasets.robotcar_dataset
import image_retrieval.rank_images
import network.network
import pose_prediction.exhaustive_search
import pose_prediction.solve_pnp
import pose_prediction.sparse_to_dense_predictor
import visualization.plot_correspondences
Macros:
==============================================================================
ROBOTCAR_ROOT = '/media/hdd/zhou/datasets'
Parameters for get_dataset_loader:
==============================================================================
get_dataset_loader.dataset_loader_cls = @robotcar_dataset.RobotCarDataset()
Parameters for ImageRetrievalModel:
==============================================================================
ImageRetrievalModel.checkpoint_path = '../checkpoints/robotcar/weights.pth.tar'
ImageRetrievalModel.encoder_dim = 512
ImageRetrievalModel.hypercolumn_layers = [14, 17, 21, 24, 28]
ImageRetrievalModel.num_clusters = 64
Parameters for RobotCarDataset:
==============================================================================
RobotCarDataset.image_folder = 'images/'
RobotCarDataset.name = 'robotcar'
RobotCarDataset.nvm_model = '/media/hdd/zhou/datasets/images/all.nvm'
RobotCarDataset.query_sequences =
['dawn',
'dusk',
'night',
'night-rain',
'overcast-summer',
'overcast-winter',
'rain',
'snow',
'sun']
RobotCarDataset.reference_sequences = ['overcast-reference']
RobotCarDataset.root = %ROBOTCAR_ROOT
RobotCarDataset.triangulation_data_file =
'../data/triangulation/robotcar_triangulation.npz'
Found existing image ranks, loading ../data/ranks/robotcar.npz
Generating pose predictions using sparse-to-dense matching...
0%| | 0/3978 [00:00<?, ?images/s]Traceback (most recent call last):
File "run.py", line 99, in
main(args)
File "run.py", line 95, in main
pose_predictor.save(pose_predictor.run())
File "/home/zhoul/S2DHM/s2dhm/pose_prediction/sparse_to_dense_predictor.py", line 129, in run
export_filename=self._dataset.output_converter(query_image))
File "/home/zhoul/S2DHM/s2dhm/pose_prediction/predictor.py", line 72, in _plot_inliers
export_filename=export_filename)
File "/home/zhoul/anaconda3/envs/s2dhm/lib/python3.7/site-packages/gin/config.py", line 1073, in gin_wrapper
utils.augment_exception_message_and_reraise(e, err_str)
File "/home/zhoul/anaconda3/envs/s2dhm/lib/python3.7/site-packages/gin/utils.py", line 49, in augment_exception_message_and_reraise
six.raise_from(proxy.with_traceback(exception.traceback), None)
File "", line 3, in raise_from
File "/home/zhoul/anaconda3/envs/s2dhm/lib/python3.7/site-packages/gin/config.py", line 1050, in gin_wrapper
return fn(*new_args, **new_kwargs)
File "/home/zhoul/S2DHM/s2dhm/visualization/plot_correspondences.py", line 41, in plot_correspondences
left_image = cv2.cvtColor(cv2.imread('left_image_path'), cv2.COLOR_BGR2RGB)
cv2.error: OpenCV(4.1.1) /io/opencv/modules/imgproc/src/color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'
In call to configurable 'plot_correspondences' (<function plot_correspondences at 0x7f82351e46a8>)
0%| | 0/3978 [00:09<?, ?images/s]
Hi,I have a question to ask you.When I do the viusalization process of running Sparse-to-dense hypercolumn matching. A error occurs.Could you tell me how to solved it?
python run.py --dataset robotcar --mode sparse_to_dense --log_images
Macros:
==============================================================================
ROBOTCAR_ROOT = '/media/hdd/zhou/datasets'
Parameters for get_dataset_loader:
==============================================================================
get_dataset_loader.dataset_loader_cls = @robotcar_dataset.RobotCarDataset()
Parameters for ImageRetrievalModel:
==============================================================================
ImageRetrievalModel.checkpoint_path = '../checkpoints/robotcar/weights.pth.tar'
ImageRetrievalModel.encoder_dim = 512
ImageRetrievalModel.hypercolumn_layers = [14, 17, 21, 24, 28]
ImageRetrievalModel.num_clusters = 64
Parameters for RobotCarDataset:
==============================================================================
RobotCarDataset.image_folder = 'images/'
RobotCarDataset.name = 'robotcar'
RobotCarDataset.nvm_model = '/media/hdd/zhou/datasets/images/all.nvm'
RobotCarDataset.query_sequences =
['dawn',
'dusk',
'night',
'night-rain',
'overcast-summer',
'overcast-winter',
'rain',
'snow',
'sun']
RobotCarDataset.reference_sequences = ['overcast-reference']
RobotCarDataset.root = %ROBOTCAR_ROOT
RobotCarDataset.triangulation_data_file =
'../data/triangulation/robotcar_triangulation.npz'
In call to configurable 'plot_correspondences' (<function plot_correspondences at 0x7f82351e46a8>)
0%| | 0/3978 [00:09<?, ?images/s]