Closed dansonZhang closed 10 months ago
Eastwind-17
commented
10 months ago I had met the same situation. Print the path in 'self.load_state_dict(torch.load(str(path)))' and then delete the file in the path. Rerun the program, it will auto download.
dansonZhang
commented
10 months ago I had met the same situation. Print the path in 'self.load_state_dict(torch.load(str(path)))' and then delete the file in the path. Rerun the program, it will auto download.
Thank you very much for your help. I have successfully solved this problem.
But with the same command, I encountered a new problem:
Computing visual neighbors... (n_neighbors = 100)
[LOG] Start 2D line detection and description (detector = deeplsd, n_images = 98)...
Traceback (most recent call last):
File "/home/danson/Code_center/limap/runners/hypersim/fitnmerge.py", line 41, in
Hello, thank you very much for providing open source code. I encountered the following error while sequentially executing QuickStart related instructions. Hope to provide assistance.
I followed the doc and continued to execute until an error occurred during this command: python runners/hypersim/fitnmerge.py --output_dir outputs/quickstart_fitnmerge
The terminal reported the following error.I guess it's because the relevant models were not downloaded (for example, I don't have the directory weight dir mentioned here:/home/danson/. limap/models), please help me.
[LOG] Number of images: 98 [LOG] Output dir: outputs/quickstart_fitnmerge [LOG] Loading dir: outputs/quickstart_fitnmerge [LOG] weight dir: /home/danson/.limap/models [SuperPoint] Extracting local features with configuration: {'model': {'max_keypoints': 4096, 'name': 'superpoint', 'nms_radius': 3}, 'output': 'feats-superpoint-n4096-r1024', 'preprocessing': {'grayscale': True, 'resize_max': 1024}} [2023/11/29 13:14:09 hloc INFO] Found 98 images in root outputs/quickstart_fitnmerge/colmap_outputs/images. Traceback (most recent call last): File "/home/danson/Code_center/limap/runners/hypersim/fitnmerge.py", line 41, in
main()
File "/home/danson/Code_center/limap/runners/hypersim/fitnmerge.py", line 38, in main
run_scene_hypersim(cfg, dataset, cfg["scene_id"], cam_id=cfg["cam_id"])
File "/home/danson/Code_center/limap/runners/hypersim/fitnmerge.py", line 14, in run_scene_hypersim
linetracks = limap.runners.line_fitnmerge(cfg, imagecols, depths)
File "/home/danson/Code_center/limap/limap/runners/line_fitnmerge.py", line 106, in linefitnmerge
, neighbors, ranges = _runners.compute_sfminfos(cfg, imagecols)
File "/home/danson/Code_center/limap/limap/runners/functions.py", line 126, in compute_sfminfos
_psfm.run_colmap_sfm_with_known_poses(cfg["sfm"], imagecols, output_path=colmap_output_path, skip_exists=cfg["skip_exists"])
File "/home/danson/Code_center/limap/limap/pointsfm/colmap_sfm.py", line 182, in run_colmap_sfm_with_known_poses
run_hloc_matches(cfg["hloc"], image_path, Path(db_path), keypoints=keypoints_in_order, neighbors=neighbors, imagecols=imagecols_tmp)
File "/home/danson/Code_center/limap/limap/pointsfm/colmap_sfm.py", line 76, in run_hloc_matches
feature_path = run_superpoint(feature_conf, image_path, outputs, keypoints=keypoints)
File "/home/danson/Code_center/limap/venv/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, kwargs)
File "/home/danson/Code_center/limap/limap/point2d/superpoint/main.py", line 55, in run_superpoint
model = SuperPoint(conf['model']).eval().to(device)
File "/home/danson/Code_center/limap/limap/point2d/superpoint/superpoint.py", line 144, in init
self.load_state_dict(torch.load(str(path)))
File "/home/danson/Code_center/limap/venv/lib/python3.9/site-packages/torch/serialization.py", line 713, in load
return _legacy_load(opened_file, map_location, pickle_module, pickle_load_args)
File "/home/danson/Code_center/limap/venv/lib/python3.9/site-packages/torch/serialization.py", line 920, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
EOFError: Ran out of input