Great work!
When I used render.py to render 30,000 rounds, I got the following error, but rendering 7,000 rounds was normal.
It is noted that at 7000 rounds, there are files point_cloud.ply and texture_map.pt, but at 30000 rounds, there are point_cloud.ply, texture_map.pt and texture_map_codebook.pt.
Looking for config file in outputs/exhibition_wall/cfg_args Config file found: outputs/exhibition_wall/cfg_args Rendering outputs/exhibition_wall Reading camera 30/30 [15/12 22:33:40] Loading Training Cameras [15/12 22:33:44] Loading Test Cameras [15/12 22:33:44] /home/fy/GS/gs-texturing/scene/gaussian_model.py:370: FutureWarning: You are using torch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
texture_map = torch.load(os.path.join(path, "texture_map.pt"))
Traceback (most recent call last):
File "/home/fy/GS/gs-texturing/render.py", line 92, in render_sets
gmodel = Controller.load_gmodel(os.path.join(dataset.model_path,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fy/GS/gs-texturing/controller.py", line 663, in load_gmodel
gmodel.load_texture_maps(path, quantize)
File "/home/fy/GS/gs-texturing/scene/gaussian_model.py", line 374, in load_texture_maps
self._texture_map = JaggedTensor(self._calculate_active_texture_resolution(powers_of_two=False).int(), texture_map.cuda())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fy/GS/gs-texturing/utils/jagged_tensor.py", line 18, in init
assert values.shape[0] == torch.prod(self._sizes, dim=1).sum().item() and values.shape[1] == data_dimensionality, "Values and sizes tensors don't match!"
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError: Values and sizes tensors don't match!
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/fy/GS/gs-texturing/render.py", line 132, in
render_sets(model.extract(args), args.iteration, pipeline.extract(args), args.skip_train, args.skip_test)
File "/home/fy/GS/gs-texturing/render.py", line 96, in render_sets
raise RuntimeError(f"Configuration {model} with name {name} not found!")
RuntimeError: Configuration baseline with name point_cloud.ply not found!`
Great work!
When I used render.py to render 30,000 rounds, I got the following error, but rendering 7,000 rounds was normal.
It is noted that at 7000 rounds, there are files point_cloud.ply and texture_map.pt, but at 30000 rounds, there are point_cloud.ply, texture_map.pt and texture_map_codebook.pt.
Looking for config file in outputs/exhibition_wall/cfg_args Config file found: outputs/exhibition_wall/cfg_args Rendering outputs/exhibition_wall Reading camera 30/30 [15/12 22:33:40] Loading Training Cameras [15/12 22:33:44] Loading Test Cameras [15/12 22:33:44] /home/fy/GS/gs-texturing/scene/gaussian_model.py:370: FutureWarning: You are usingtorch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.texture_map = torch.load(os.path.join(path, "texture_map.pt"))
Traceback (most recent call last):
File "/home/fy/GS/gs-texturing/render.py", line 92, in render_sets
gmodel = Controller.load_gmodel(os.path.join(dataset.model_path,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fy/GS/gs-texturing/controller.py", line 663, in load_gmodel
gmodel.load_texture_maps(path, quantize)
File "/home/fy/GS/gs-texturing/scene/gaussian_model.py", line 374, in load_texture_maps
self._texture_map = JaggedTensor(self._calculate_active_texture_resolution(powers_of_two=False).int(), texture_map.cuda())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fy/GS/gs-texturing/utils/jagged_tensor.py", line 18, in init
assert values.shape[0] == torch.prod(self._sizes, dim=1).sum().item() and values.shape[1] == data_dimensionality, "Values and sizes tensors don't match!"
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError: Values and sizes tensors don't match!
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/fy/GS/gs-texturing/render.py", line 132, in
render_sets(model.extract(args), args.iteration, pipeline.extract(args), args.skip_train, args.skip_test)
File "/home/fy/GS/gs-texturing/render.py", line 96, in render_sets
raise RuntimeError(f"Configuration {model} with name {name} not found!")
RuntimeError: Configuration baseline with name point_cloud.ply not found!`