search

autonomousvision / occupancy_networks

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"
https://avg.is.tuebingen.mpg.de/publications/occupancy-networks
MIT License
1.49k stars 291 forks source link

Training Problem #50

Open sosown123 opened 4 years ago

sosown123 commented 4 years ago

I download the Preprocessed data and unzip it to the data/ShapeNet folder I met some problems in the following messages, could you help me? It seems like that i did not load the data

File "/media/mickyv2/micky/occupancy_networks-master/train.py", line 70, in data_vis = next(iter(vis_loader)) File "/home/mickyv2/anaconda3/envs/mesh_funcspace/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 615, in next batch = self.collate_fn([self.dataset[i] for i in indices]) File "/media/mickyv2/micky/occupancy_networks-master/im2mesh/data/core.py", line 169, in collate_remove_none return data.dataloader.default_collate(batch) File "/home/mickyv2/anaconda3/envs/mesh_funcspace/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 200, in default_collate elem_type = type(batch[0]) IndexError: list index out of range

mnunezu commented 4 years ago

I solve it, you have to specify the img_folder corresponding in the dataset.

in the case of core dataset img_folder: img_choy2016

NaveedMaz commented 3 years ago

@mnunezu can you please specify which line and where i am noob in this. so please help

tiexuedanxin commented 3 years ago

@mnunezu can you please specify which line and where i am noob in this. so please help

hello, Have you solve the problem? I get the same error but don't know how to solve it.

NaveedMaz commented 3 years ago

yes i solved that issue but the problem is that i managed to get the chamfer loss 0.0016 and that is very low on pixel2mesh implementation inside this repo but i am unable to draw predictions using this trained model. it needs camera configuration points which it should not need during prediction. Anyone could help me with this?

tiexuedanxin commented 3 years ago

yes i solved that issue but the problem is that i managed to get the chamfer loss 0.0016 and that is very low on pixel2mesh implementation inside this repo but i am unable to draw predictions using this trained model. it needs camera configuration points which it should not need during prediction. Anyone could help me with this?

Could you tell me how you solve it?

NaveedMaz commented 3 years ago

yes, sure you have to change the img dir in your configuration file. such as img_folder: img_choy2016

NaveedMaz commented 3 years ago

i hope it helps otherwise i can send you the file or email you if you like. just a quick suggestion rather wasting time on it you can always to and check out pytorch3d

tiexuedanxin commented 3 years ago

i hope it helps otherwise i can send you the file or email you if you like. just a quick suggestion rather wasting time on it you can always to and check out pytorch3d

hello, my eamil address is 740337741@qq.com, very thank you for send me the file.

tiexuedanxin commented 3 years ago

i hope it helps otherwise i can send you the file or email you if you like. just a quick suggestion rather wasting time on it you can always to and check out pytorch3d

hello, please help.

tiexuedanxin commented 3 years ago

i hope it helps otherwise i can send you the file or email you if you like. just a quick suggestion rather wasting time on it you can always to and check out pytorch3d

hello,