shunsukesaito / PIFu

This repository contains the code for the paper "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization"
https://shunsukesaito.github.io/PIFu/
Other
1.75k stars 343 forks source link

sh ./scripts/test.sh error #153

Open Ishihara-Masabumi opened 1 year ago

Ishihara-Masabumi commented 1 year ago

When I tried to run sh ./scripts/test.sh, the following error occurred.

$ sh ./scripts/test.sh
+ GPU_ID=0
+ DISPLAY_ID=10
+ NAME=pifu_demo
+ BATCH_SIZE=1
+ MLP_DIM=257 1024 512 256 128 1
+ MLP_DIM_COLOR=513 1024 512 256 128 3
+ VOL_RES=256
+ CHECKPOINTS_NETG_PATH=./checkpoints/net_G
+ CHECKPOINTS_NETC_PATH=./checkpoints/net_C
+ TEST_FOLDER_PATH=./sample_images
+ CUDA_VISIBLE_DEVICES=0 python ./apps/eval.py --name pifu_demo --batch_size 1 --mlp_dim 257 1024 512 256 128 1 --mlp_dim_color 513 1024 512 256 128 3 --num_stack 4 --num_hourglass 2 --resolution 256 --hg_down ave_pool --norm group --norm_color group --test_folder_path ./sample_images --load_netG_checkpoint_path ./checkpoints/net_G --load_netC_checkpoint_path ./checkpoints/net_C
/home/dl/miniconda3/envs/plfu/lib/python3.8/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: /home/dl/miniconda3/envs/plfu/lib/python3.8/site-packages/torchvision/image.so: undefined symbol: _ZN5torch3jit17parseSchemaOrNameERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE
  warn(f"Failed to load image Python extension: {e}")
initialize network with normal
Using Network:  hgpifu
loading for net C ... ./checkpoints/net_C
initialize network with normal
num;  1
0it [00:00, ?it/s]./sample_images/ryota.png ./sample_images/ryota_mask.png
/home/dl/plfu/PIFu/lib/sdf.py:58: FutureWarning: In the future `np.bool` will be defined as the corresponding NumPy scalar.
  dirty = np.ones(resolution, dtype=np.bool)
module 'numpy' has no attribute 'bool'.
`np.bool` was a deprecated alias for the builtin `bool`. To avoid this error in existing code, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
    https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
Can not create marching cubes at this time.
1it [00:02,  2.61s/it]

Please fix it.

River-Zhang commented 7 months ago

change measure.marching_cubes_lewiner to measure.marching_cubes would work for me, you can try this