How to evaluate pretrained model on custom objects.

[Prerana-jo]

I have replaced the objects in the test folder with some of my custom objects. I have ensured that they are in the same file format as the test objects provided. My models folder contains

• model_normalized_graspobject_collision.obj
• model_normalized_graspobject.obj
• model_normalized_graspobject.urdf

When I run the following command -
python evaluate_generator.py --evaluate_config configs/evaluate.json --objects test/ --name evaluation_results
I get the following error -
pybullet build time: Oct 8 2020 00:10:46
2024-11-04 10:23:36,578 INFO resource_spec.py:212 -- Starting Ray with 3.71 GiB memory available for workers and up to 1.86 GiB for objects. You can adjust these settings with ray.init(memory=, object_store_memory=).
2024-11-04 10:23:36,913 INFO services.py:1170 -- View the Ray dashboard at localhost:8265
configs/default.json
[ObjectDataset] globbing grasp objects ...
[ObjectDataset] found 4 objects
checking grasp objects ...: 100%|██████████████████████████████████████| 4/4 [00:01<00:00, 2.82it/s]
[ObjectDataset] found 4 bad objects
Traceback (most recent call last):
File "evaluate_generator.py", line 97, in
batch_size=args.objects_bs,
File "/home/aica/fit2form-master/learning/utils.py", line 68, in init
collate_fn=lambda batch: batch)
File "/home/aica/miniconda3/envs/fit2form/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 224, in init
sampler = RandomSampler(dataset, generator=generator)
File "/home/aica/miniconda3/envs/fit2form/lib/python3.7/site-packages/torch/utils/data/sampler.py", line 96, in init
"value, but got num_samples={}".format(self.num_samples))
ValueError: num_samples should be a positive integer value, but got num_samples=0

Why are my objects being classified as bad objects?
I also see that there is no tsdf.npy file for my objects and I do not know how to generate these. Could someone please help me out with this.