MeshCNN icon indicating copy to clipboard operation
MeshCNN copied to clipboard

Error at merge_prepare.py

Open Noxx23 opened this issue 2 years ago • 4 comments

Hi, i got an error with this file when i want to use train.sh

------------ Options ------------- arch: meshunet batch_size: 2 beta1: 0.9 checkpoints_dir: ./checkpoints continue_train: False dataroot: datasets/human_seg dataset_mode: segmentation epoch_count: 1 export_folder: fc_n: 100 flip_edges: 0 gpu_ids: [] init_gain: 0.02 init_type: normal is_train: True lr: 0.001 lr_decay_iters: 50 lr_policy: lambda max_dataset_size: inf name: human_seg ncf: [32, 64, 128, 256] ninput_edges: 3000 niter: 100 niter_decay: 500 no_vis: False norm: batch num_aug: 20 num_groups: 16 num_threads: 0 phase: train pool_res: [2000, 1000, 500] print_freq: 10 resblocks: 1 run_test_freq: 1 save_epoch_freq: 1 save_latest_freq: 250 scale_verts: False seed: None serial_batches: False slide_verts: 0.2 verbose_plot: True weighted_loss: [0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125] which_epoch: latest -------------- End ---------------- computing mean std from train data... Traceback (most recent call last): File "C:\Users\seanb\OneDrive\Documents\GitHub\MedMeshCNN\train.py", line 11, in dataset = DataLoader(opt) File "C:\Users\seanb\OneDrive\Documents\GitHub\MedMeshCNN\data_init_.py", line 21, in init self.dataset = CreateDataset(opt) File "C:\Users\seanb\OneDrive\Documents\GitHub\MedMeshCNN\data_init_.py", line 9, in CreateDataset dataset = SegmentationData(opt) File "C:\Users\seanb\OneDrive\Documents\GitHub\MedMeshCNN\data\segmentation_data.py", line 22, in init self.get_mean_std() File "C:\Users\seanb\OneDrive\Documents\GitHub\MedMeshCNN\data\base_dataset.py", line 32, in get_mean_std for i, data in enumerate(self): File "C:\Users\seanb\OneDrive\Documents\GitHub\MedMeshCNN\data\segmentation_data.py", line 29, in getitem mesh = Mesh(file=path, opt=self.opt, hold_history=True, export_folder=self.opt.export_folder) File "C:\Users\seanb\OneDrive\Documents\GitHub\MedMeshCNN\models\layers\mesh.py", line 16, in init fill_mesh(self, file, opt) File "C:\Users\seanb\OneDrive\Documents\GitHub\MedMeshCNN\models\layers\mesh_prepare.py", line 21, in fill_mesh mesh2fill.ve = mesh_data['ve'] File "C:\Users\seanb\anaconda3\lib\site-packages\numpy\lib\npyio.py", line 260, in getitem raise KeyError("%s is not a file in the archive" % key) KeyError: 've is not a file in the archive'

Noxx23 avatar Jan 05 '23 14:01 Noxx23

I met this problem too. Why? I ran the code in windows system.

JfanLiu avatar Aug 30 '23 15:08 JfanLiu

I also met this problem, so do all my classmates. But I ran it in WSL. The error information is the same. How can I solve it? Thx

SplenDidMav avatar Jan 17 '24 11:01 SplenDidMav

I also encountered this issue,how to solve it?Thx

tyla881 avatar May 29 '24 09:05 tyla881

for me this error was resolved by downgrading numpy to the required version

rongithubbed avatar Jul 18 '24 11:07 rongithubbed