Train own dataset with CUDA 12 installed

[matthiasjaeger95]

Hello,

Thank you for the very interesting repository.

I am currently trying to train the network with my own data set. However, when I try to run the pretrain_treegan.py script I get the following error:

NOTE: EMD not installed yet 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 689/689 [00:00<00:00, 16413.59it/s] Training Dataset : 689 prepared. Network prepared. Traceback (most recent call last): File "pretrain_treegan.py", line 214, in model.run(save_ckpt=SAVE_CHECKPOINT, load_ckpt=LOAD_CHECKPOINT) File "pretrain_treegan.py", line 69, in run checkpoint = torch.load(load_ckpt, map_location=self.args.device) File "/home/b111/anaconda3/envs/shapeinversion/lib/python3.7/site-packages/torch/serialization.py", line 386, in load return _load(f, map_location, pickle_module, **pickle_load_args) File "/home/b111/anaconda3/envs/shapeinversion/lib/python3.7/site-packages/torch/serialization.py", line 580, in _load deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly) RuntimeError: storage has wrong size: expected 0 got 32768

Could you help me to solve the problem?

Thank you very much in advance. Matthias