Not finding images

[Snapisch]

I am getting the following error and guess it is because I somehow have the wrong file path. I already tried pretty much all combinations, so maybe you can help me with the correct path name.

Creating output directory... Launching processes... Setting up PyTorch plugin "upfirdn2d_plugin"... Done. Setting up PyTorch plugin "bias_act_plugin"... Done. Setting up PyTorch plugin "filtered_lrelu_plugin"... Done. Loading training set... ==> use shapenet dataset ==> use shapenet folder number 0 ==> use image path: input/relief_data_rendered/img, num images: 0 Traceback (most recent call last): File "train_3d.py", line 330, in main() # pylint: disable=no-value-for-parameter File "/home/jumo261b/.conda/envs/get3d/lib/python3.8/site-packages/click/core.py", line 1130, in call return self.main(args, kwargs) File "/home/jumo261b/.conda/envs/get3d/lib/python3.8/site-packages/click/core.py", line 1055, in main rv = self.invoke(ctx) File "/home/jumo261b/.conda/envs/get3d/lib/python3.8/site-packages/click/core.py", line 1404, in invoke return ctx.invoke(self.callback, ctx.params) File "/home/jumo261b/.conda/envs/get3d/lib/python3.8/site-packages/click/core.py", line 760, in invoke return __callback(args, kwargs) File "train_3d.py", line 324, in main launch_training(c=c, desc=desc, outdir=opts.outdir, dry_run=opts.dry_run) File "train_3d.py", line 103, in launch_training subprocess_fn(rank=0, c=c, temp_dir=temp_dir) File "train_3d.py", line 49, in subprocess_fn training_loop_3d.training_loop(rank=rank, c) File "/home/h3/jumo261b/GET3D/training/training_loop_3d.py", line 134, in training_loop training_set_sampler = misc.InfiniteSampler( File "/home/h3/jumo261b/GET3D/torch_utils/misc.py", line 120, in init assert len(dataset) > 0 AssertionError

Used command: python train_3d.py --outdir=log --data=input/relief_data_rendered/img --camera_path input/relief_data_rendered/camera --gpus=1 --batch=32 --gamma=40 --data_camera_mode shapenet_car --dmtet_scale 1.0 --use_shapenet_split 1 --one_3d_generator 1 --fp32 0

Project structure: input -relief_data_rendered --img ---Version1 ----deva-capitoline-wolf-bas-Romania -----000.png -----...

[SteveJunGao]

Hi @Snapisch ,

According to your folder structure, you need to set --data=input/relief_data_rendered/img/Version1 and --camera_path =input/relief_data_rendered/camera, let me know if this works or not ;) !

[Snapisch]

Unfortunately this does not work for me, I still get the same error. But in theory the path should point to the folder where all the different folders for the input models are contained, no?

Here is a more detailed view of my project structure: GET3D -train_3d.py -input --relief_data_rendered ---img ----Version1 -----deva-capitoline-wolf-bas-Romania ------000.png ------001.png ------... ------transforms.json -----god-Ashur-neues-museum-relief ------000.png ------001.png ------... ------transforms.json

[Dandelionym]

Hi, Snapisch.

@Snapisch Have you solved this problem?

[Snapisch]

Hello,

thanks for reminding me. My problem was caused by not properly configuring the files in 3dgan_data_split, since I did not use the shapenet dataset. Now everything is working properly. But thanks for your help ^^