Open leelang7 opened 3 years ago
@leelang7 Do you have 4 GPUs in your server? The script would require 4 GPUs by default. If not, you may change the script to:
python run.py \
--config configs/${CONFIG}.yml \
2>&1 | tee results/${EXP}/log.txt
Besides, make sure to run sh script/download.sh
before running other scripts.
i tried but i got the same result.
StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback. Load config from yml file: configs/car.yml Loading configs from configs/car.yml {'checkpoint_dir': 'results/car', 'save_checkpoint_freq': 500, 'keep_num_checkpoint': 2, 'use_logger': True, 'log_freq': 100, 'joint_train': False, 'independent': False, 'reset_weight': True, 'save_results': True, 'num_stage': 4, 'flip1_cfg': [False, False, False, False], 'flip3_cfg': [False, False, False, False], 'stage_len_dict': {'step1': 700, 'step2': 700, 'step3': 600}, 'stage_len_dict2': {'step1': 200, 'step2': 500, 'step3': 400}, 'image_size': 128, 'load_gt_depth': False, 'img_list_path': 'data/car/list.txt', 'img_root': 'data/car', 'latent_root': 'data/car/latents', 'model_name': 'gan2shape_car', 'category': 'car', 'share_weight': True, 'relative_enc': False, 'use_mask': True, 'add_mean_L': True, 'add_mean_V': True, 'min_depth': 0.9, 'max_depth': 1.1, 'xyz_rotation_range': 60, 'xy_translation_range': 0.1, 'z_translation_range': 0, 'collect_iters': 100, 'batchsize': 8, 'lr': 0.0001, 'lam_perc': 0.5, 'lam_smooth': 0.01, 'lam_regular': 0.01, 'view_mvn_path': 'checkpoints/view_light/view_mvn.pth', 'light_mvn_path': 'checkpoints/view_light/light_mvn.pth', 'channel_multiplier': 2, 'gan_size': 512, 'gan_ckpt': 'checkpoints/stylegan2/stylegan2-car-config-f.pt', 'F1_d': 2, 'rot_center_depth': 1.0, 'fov': 10, 'tex_cube_size': 2, 'config': 'configs/car.yml', 'seed': 0, 'num_workers': 4, 'distributed': False} Setting up Perceptual loss... Loading model from: /content/drive/My Drive/GAN2Shape/gan2shape/stylegan2/stylegan2-pytorch/lpips/weights/v0.1/vgg.pth ...[net-lin [vgg]] initialized ...Done Loading images... Initializing the depth net to output ellipsoid ... Iter: 0, Loss: 0.001553 Iter: 100, Loss: 0.000014 Iter: 200, Loss: 0.000011 Iter: 300, Loss: 0.000026 Iter: 400, Loss: 0.000009 Iter: 500, Loss: 0.000010 Iter: 600, Loss: 0.000008 Iter: 700, Loss: 0.000008 Iter: 800, Loss: 0.000008 Iter: 900, Loss: 0.000008 E0000/T00000/step1/ 0.0Hz loss: 1.05303 E0000/T00001/step1/ 0.1Hz loss: 1.04649 E0000/T00002/step1/ 0.7Hz loss: 1.03471 E0000/T00003/step1/ 1.2Hz loss: 1.01915 E0000/T00004/step1/ 1.7Hz loss: 1.00167 E0000/T00005/step1/ 2.1Hz loss: 0.98326 E0000/T00006/step1/ 2.5Hz loss: 0.96459 E0000/T00007/step1/ 2.8Hz loss: 0.94606 E0000/T00008/step1/ 3.1Hz loss: 0.92788 E0000/T00009/step1/ 3.4Hz loss: 0.91007 E0000/T00010/step1/ 3.7Hz loss: 0.89263 E0000/T00011/step1/ 3.9Hz loss: 0.87544 E0000/T00012/step1/ 4.1Hz loss: 0.85845 E0000/T00013/step1/ 4.3Hz loss: 0.84165 E0000/T00014/step1/ 4.4Hz loss: 0.82490 E0000/T00015/step1/ 4.6Hz loss: 0.80816 E0000/T00016/step1/ 4.7Hz loss: 0.79124 E0000/T00017/step1/ 4.8Hz loss: 0.77385 E0000/T00018/step1/ 4.9Hz loss: 0.75603 E0000/T00019/step1/ 5.0Hz loss: 0.73793 E0000/T00020/step1/ 5.1Hz loss: 0.71979 E0000/T00021/step1/ 5.2Hz loss: 0.70169 E0000/T00022/step1/ 5.3Hz loss: 0.68356 E0000/T00023/step1/ 5.3Hz loss: 0.66546 E0000/T00024/step1/ 5.4Hz loss: 0.64739 E0000/T00025/step1/ 5.5Hz loss: 0.62937 E0000/T00026/step1/ 5.5Hz loss: 0.61140 E0000/T00027/step1/ 5.5Hz loss: 0.59349 E0000/T00028/step1/ 5.6Hz loss: 0.57570 E0000/T00029/step1/ 5.6Hz loss: 0.55801 E0000/T00030/step1/ 5.7Hz loss: 0.54044 E0000/T00031/step1/ 5.7Hz loss: 0.52303 E0000/T00032/step1/ 5.7Hz loss: 0.50588 E0000/T00033/step1/ 5.7Hz loss: 0.48904 E0000/T00034/step1/ 5.7Hz loss: 0.47253 E0000/T00035/step1/ 5.7Hz loss: 0.45641 E0000/T00036/step1/ 5.7Hz loss: 0.44073 E0000/T00037/step1/ 5.8Hz loss: 0.42551 E0000/T00038/step1/ 5.8Hz loss: 0.41077 E0000/T00039/step1/ 5.8Hz loss: 0.3965 . . .
!sh scripts/run_car.sh
StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback.
Load config from yml file: configs/car.yml
Loading configs from configs/car.yml
{'checkpoint_dir': 'results/car', 'save_checkpoint_freq': 500, 'keep_num_checkpoint': 2, 'use_logger': True, 'log_freq': 100, 'joint_train': False, 'independent': False, 'reset_weight': True, 'save_results': True, 'num_stage': 4, 'flip1_cfg': [False, False, False, False], 'flip3_cfg': [False, False, False, False], 'stage_len_dict': {'step1': 700, 'step2': 700, 'step3': 600}, 'stage_len_dict2': {'step1': 200, 'step2': 500, 'step3': 400}, 'image_size': 128, 'load_gt_depth': False, 'img_list_path': 'data/car/list.txt', 'img_root': 'data/car', 'latent_root': 'data/car/latents', 'model_name': 'gan2shape_car', 'category': 'car', 'share_weight': True, 'relative_enc': False, 'use_mask': True, 'add_mean_L': True, 'add_mean_V': True, 'min_depth': 0.9, 'max_depth': 1.1, 'xyz_rotation_range': 60, 'xy_translation_range': 0.1, 'z_translation_range': 0, 'collect_iters': 100, 'batchsize': 8, 'lr': 0.0001, 'lam_perc': 0.5, 'lam_smooth': 0.01, 'lam_regular': 0.01, 'view_mvn_path': 'checkpoints/view_light/view_mvn.pth', 'light_mvn_path': 'checkpoints/view_light/light_mvn.pth', 'channel_multiplier': 2, 'gan_size': 512, 'gan_ckpt': 'checkpoints/stylegan2/stylegan2-car-config-f.pt', 'F1_d': 2, 'rot_center_depth': 1.0, 'fov': 10, 'tex_cube_size': 2, 'config': 'configs/car.yml', 'seed': 0, 'num_workers': 4, 'distributed': True}
Load config from yml file: configs/car.yml
Loading configs from configs/car.yml
Load config from yml file: configs/car.yml
Loading configs from configs/car.yml
Load config from yml file: configs/car.yml
Loading configs from configs/car.yml
{'checkpoint_dir': 'results/car', 'save_checkpoint_freq': 500, 'keep_num_checkpoint': 2, 'use_logger': True, 'log_freq': 100, 'joint_train': False, 'independent': False, 'reset_weight': True, 'save_results': True, 'num_stage': 4, 'flip1_cfg': [False, False, False, False], 'flip3_cfg': [False, False, False, False], 'stage_len_dict': {'step1': 700, 'step2': 700, 'step3': 600}, 'stage_len_dict2': {'step1': 200, 'step2': 500, 'step3': 400}, 'image_size': 128, 'load_gt_depth': False, 'img_list_path': 'data/car/list.txt', 'img_root': 'data/car', 'latent_root': 'data/car/latents', 'model_name': 'gan2shape_car', 'category': 'car', 'share_weight': True, 'relative_enc': False, 'use_mask': True, 'add_mean_L': True, 'add_mean_V': True, 'min_depth': 0.9, 'max_depth': 1.1, 'xyz_rotation_range': 60, 'xy_translation_range': 0.1, 'z_translation_range': 0, 'collect_iters': 100, 'batchsize': 8, 'lr': 0.0001, 'lam_perc': 0.5, 'lam_smooth': 0.01, 'lam_regular': 0.01, 'view_mvn_path': 'checkpoints/view_light/view_mvn.pth', 'light_mvn_path': 'checkpoints/view_light/light_mvn.pth', 'channel_multiplier': 2, 'gan_size': 512, 'gan_ckpt': 'checkpoints/stylegan2/stylegan2-car-config-f.pt', 'F1_d': 2, 'rot_center_depth': 1.0, 'fov': 10, 'tex_cube_size': 2, 'config': 'configs/car.yml', 'seed': 0, 'num_workers': 4, 'distributed': True}
Traceback (most recent call last):
File "run.py", line 26, in
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
@leelang7 For the first error, you should specify what ${CONFIG} and ${EXP} are. For example:
python run.py \
--config configs/car.yml \
2>&1 | tee results/car/log.txt
For the second error, you may try changing the value of PORT in the script to another value.
We are running this on google colab and I tried changing the run_car.sh to run for 1 GPU : run_car.sh
EXP=car
CONFIG=car
GPUS=1
PORT=${PORT:-29578}
mkdir -p results/${EXP}
python run.py \
--config configs/${CONFIG}.yml \
2>&1 | tee results/${EXP}/log.txt
The error we get is:
Load config from yml file: configs/car.yml
Loading configs from configs/car.yml
{'checkpoint_dir': 'results/car', 'save_checkpoint_freq': 500, 'keep_num_checkpoint': 2, 'use_logger': True, 'log_freq': 100, 'joint_train': False, 'independent': False, 'reset_weight': True, 'save_results': True, 'num_stage': 4, 'flip1_cfg': [False, False, False, False], 'flip3_cfg': [False, False, False, False], 'stage_len_dict': {'step1': 700, 'step2': 700, 'step3': 600}, 'stage_len_dict2': {'step1': 200, 'step2': 500, 'step3': 400}, 'image_size': 128, 'load_gt_depth': False, 'img_list_path': 'data/car/list.txt', 'img_root': 'data/car', 'latent_root': 'data/car/latents', 'model_name': 'gan2shape_car', 'category': 'car', 'share_weight': True, 'relative_enc': False, 'use_mask': True, 'add_mean_L': True, 'add_mean_V': True, 'min_depth': 0.9, 'max_depth': 1.1, 'xyz_rotation_range': 60, 'xy_translation_range': 0.1, 'z_translation_range': 0, 'collect_iters': 100, 'batchsize': 8, 'lr': 0.0001, 'lam_perc': 0.5, 'lam_smooth': 0.01, 'lam_regular': 0.01, 'view_mvn_path': 'checkpoints/view_light/view_mvn.pth', 'light_mvn_path': 'checkpoints/view_light/light_mvn.pth', 'rand_light': [-1, 1, -0.2, 0.8, -0.1, 0.6, -0.6], 'channel_multiplier': 2, 'gan_size': 512, 'gan_ckpt': 'checkpoints/stylegan2/stylegan2-car-config-f.pt', 'F1_d': 2, 'rot_center_depth': 1.0, 'fov': 10, 'tex_cube_size': 2, 'config': 'configs/car.yml', 'seed': 0, 'num_workers': 4, 'distributed': False}
Setting up Perceptual loss...
Loading model from: /content/GAN2Shape/gan2shape/stylegan2/stylegan2-pytorch/lpips/weights/v0.1/vgg.pth
...[net-lin [vgg]] initialized
...Done
Traceback (most recent call last):
File "run.py", line 31, in
Can you please tell us what changes need to be made or what port number should be changed?
We are running this on google colab and I tried changing the run_car.sh to run for 1 GPU : run_car.sh
EXP=car CONFIG=car GPUS=1 PORT=${PORT:-29578} mkdir -p results/${EXP} python run.py \ --config configs/${CONFIG}.yml \ 2>&1 | tee results/${EXP}/log.txt
The error we get is: Load config from yml file: configs/car.yml Loading configs from configs/car.yml {'checkpoint_dir': 'results/car', 'save_checkpoint_freq': 500, 'keep_num_checkpoint': 2, 'use_logger': True, 'log_freq': 100, 'joint_train': False, 'independent': False, 'reset_weight': True, 'save_results': True, 'num_stage': 4, 'flip1_cfg': [False, False, False, False], 'flip3_cfg': [False, False, False, False], 'stage_len_dict': {'step1': 700, 'step2': 700, 'step3': 600}, 'stage_len_dict2': {'step1': 200, 'step2': 500, 'step3': 400}, 'image_size': 128, 'load_gt_depth': False, 'img_list_path': 'data/car/list.txt', 'img_root': 'data/car', 'latent_root': 'data/car/latents', 'model_name': 'gan2shape_car', 'category': 'car', 'share_weight': True, 'relative_enc': False, 'use_mask': True, 'add_mean_L': True, 'add_mean_V': True, 'min_depth': 0.9, 'max_depth': 1.1, 'xyz_rotation_range': 60, 'xy_translation_range': 0.1, 'z_translation_range': 0, 'collect_iters': 100, 'batchsize': 8, 'lr': 0.0001, 'lam_perc': 0.5, 'lam_smooth': 0.01, 'lam_regular': 0.01, 'view_mvn_path': 'checkpoints/view_light/view_mvn.pth', 'light_mvn_path': 'checkpoints/view_light/light_mvn.pth', 'rand_light': [-1, 1, -0.2, 0.8, -0.1, 0.6, -0.6], 'channel_multiplier': 2, 'gan_size': 512, 'gan_ckpt': 'checkpoints/stylegan2/stylegan2-car-config-f.pt', 'F1_d': 2, 'rot_center_depth': 1.0, 'fov': 10, 'tex_cube_size': 2, 'config': 'configs/car.yml', 'seed': 0, 'num_workers': 4, 'distributed': False} Setting up Perceptual loss... Loading model from: /content/GAN2Shape/gan2shape/stylegan2/stylegan2-pytorch/lpips/weights/v0.1/vgg.pth ...[net-lin [vgg]] initialized ...Done Traceback (most recent call last): File "run.py", line 31, in trainer = Trainer(cfgs, GAN2Shape) File "/content/GAN2Shape/gan2shape/trainer.py", line 23, in init self.model = model(cfgs) File "/content/GAN2Shape/gan2shape/model.py", line 92, in init self.renderer = Renderer(cfgs, self.image_size) File "/content/GAN2Shape/gan2shape/renderer/renderer.py", line 46, in init self.inv_K = self.inv_K_origin.clone() RuntimeError: CUDA error: invalid device function
Can you please tell us what changes need to be made or what port number should be changed?
I meet the same problem, so, I wanna know, have you solved this?And, what's the version of your cuda, cudnn, torch?
I tested in linux-server.. it was the same in co lab setting.(same to unsup3d) <-- pytorch 1.2
sh scripts/run_car.sh No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda' No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda' No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda' No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda' StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback. Load config from yml file: configs/car.yml Loading configs from configs/car.yml Traceback (most recent call last): File "run.py", line 26, in
init_dist(args.launcher, backend='nccl')
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/site-packages/mmcv/runner/dist_utils.py", line 20, in init_dist
_init_dist_pytorch(backend, kwargs)
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/site-packages/mmcv/runner/dist_utils.py", line 33, in _init_dist_pytorch
torch.cuda.set_device(rank % num_gpus)
ZeroDivisionError: integer division or modulo by zero
Load config from yml file: configs/car.yml
Loading configs from configs/car.yml
Traceback (most recent call last):
File "run.py", line 26, in
init_dist(args.launcher, backend='nccl')
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/site-packages/mmcv/runner/dist_utils.py", line 20, in init_dist
_init_dist_pytorch(backend, kwargs)
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/site-packages/mmcv/runner/dist_utils.py", line 33, in _init_dist_pytorch
torch.cuda.set_device(rank % num_gpus)
ZeroDivisionError: integer division or modulo by zero
Load config from yml file: configs/car.yml
Loading configs from configs/car.yml
Traceback (most recent call last):
File "run.py", line 26, in
init_dist(args.launcher, backend='nccl')
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/site-packages/mmcv/runner/dist_utils.py", line 20, in init_dist
_init_dist_pytorch(backend, kwargs)
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/site-packages/mmcv/runner/dist_utils.py", line 33, in _init_dist_pytorch
torch.cuda.set_device(rank % num_gpus)
ZeroDivisionError: integer division or modulo by zero
Load config from yml file: configs/car.yml
Loading configs from configs/car.yml
Traceback (most recent call last):
File "run.py", line 26, in
init_dist(args.launcher, backend='nccl')
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/site-packages/mmcv/runner/dist_utils.py", line 20, in init_dist
_init_dist_pytorch(backend, kwargs)
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/site-packages/mmcv/runner/dist_utils.py", line 33, in _init_dist_pytorch
torch.cuda.set_device(rank % num_gpus)
ZeroDivisionError: integer division or modulo by zero
Traceback (most recent call last):
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/site-packages/torch/distributed/launch.py", line 246, in
main()
File "/home/adminuser/anaconda3/envs/3D/lib/python3.6/site-packages/torch/distributed/launch.py", line 242, in main
cmd=cmd)
subprocess.CalledProcessError: Command '['/home/adminuser/anaconda3/envs/3D/bin/python', '-u', 'run.py', '--local_rank=3', '--launcher', 'pytorch', '--config', 'configs/car.yml']' returned non-zero exit status 1.
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
sh scripts/run_car.sh <-- pytorch 1.1 StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback. Traceback (most recent call last): File "run.py", line 7, in
from gan2shape import setup_runtime, Trainer, GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/init.py", line 3, in
from .model import GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/model.py", line 17, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/init.py", line 1, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/renderer.py", line 6, in
import neural_renderer as nr
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/init.py", line 3, in
from .load_obj import load_obj
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/load_obj.py", line 8, in
import neural_renderer.cuda.load_textures as load_textures_cuda
ImportError: libcudart.so.9.2: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "run.py", line 7, in
from gan2shape import setup_runtime, Trainer, GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/init.py", line 3, in
from .model import GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/model.py", line 17, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/init.py", line 1, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/renderer.py", line 6, in
import neural_renderer as nr
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/init.py", line 3, in
from .load_obj import load_obj
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/load_obj.py", line 8, in
import neural_renderer.cuda.load_textures as load_textures_cuda
ImportError: libcudart.so.9.2: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "run.py", line 7, in
from gan2shape import setup_runtime, Trainer, GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/init.py", line 3, in
from .model import GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/model.py", line 17, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/init.py", line 1, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/renderer.py", line 6, in
import neural_renderer as nr
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/init.py", line 3, in
from .load_obj import load_obj
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/load_obj.py", line 8, in
import neural_renderer.cuda.load_textures as load_textures_cuda
ImportError: libcudart.so.9.2: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "run.py", line 7, in
from gan2shape import setup_runtime, Trainer, GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/init.py", line 3, in
from .model import GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/model.py", line 17, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/init.py", line 1, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/renderer.py", line 6, in
import neural_renderer as nr
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/init.py", line 3, in
from .load_obj import load_obj
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/load_obj.py", line 8, in
import neural_renderer.cuda.load_textures as load_textures_cuda
ImportError: libcudart.so.9.2: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/torch/distributed/launch.py", line 235, in
main()
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/torch/distributed/launch.py", line 231, in main
cmd=process.args)
subprocess.CalledProcessError: Command '['/home/adminuser/anaconda3/envs/test/bin/python', '-u', 'run.py', '--local_rank=0', '--launcher', 'pytorch', '--config', 'configs/car.yml']' returned non-zero exit status 1.
(test) adminuser@DGX-Station:~/GAN2Shape$ python run.py --config /configs/car.yml
StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback.
Traceback (most recent call last):
File "run.py", line 7, in
from gan2shape import setup_runtime, Trainer, GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/init.py", line 3, in
from .model import GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/model.py", line 17, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/init.py", line 1, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/renderer.py", line 6, in
import neural_renderer as nr
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/init.py", line 3, in
from .load_obj import load_obj
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/load_obj.py", line 8, in
import neural_renderer.cuda.load_textures as load_textures_cuda
ImportError: libcudart.so.9.2: cannot open shared object file: No such file or directory
(test) adminuser@DGX-Station:~/GAN2Shape$
(test) adminuser@DGX-Station:~/GAN2Shape$ ^C
(test) adminuser@DGX-Station:~/GAN2Shape$
(test) adminuser@DGX-Station:~/GAN2Shape$ sh scripts/run_car.sh
StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback.
StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback.
Traceback (most recent call last):
File "run.py", line 7, in
from gan2shape import setup_runtime, Trainer, GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/init.py", line 3, in
from .model import GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/model.py", line 17, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/init.py", line 1, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/renderer.py", line 6, in
import neural_renderer as nr
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/init.py", line 3, in
from .load_obj import load_obj
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/load_obj.py", line 8, in
import neural_renderer.cuda.load_textures as load_textures_cuda
ImportError: libcudart.so.9.2: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "run.py", line 7, in
from gan2shape import setup_runtime, Trainer, GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/init.py", line 3, in
from .model import GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/model.py", line 17, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/init.py", line 1, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/renderer.py", line 6, in
import neural_renderer as nr
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/init.py", line 3, in
from .load_obj import load_obj
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/load_obj.py", line 8, in
import neural_renderer.cuda.load_textures as load_textures_cuda
ImportError: libcudart.so.9.2: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "run.py", line 7, in
from gan2shape import setup_runtime, Trainer, GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/init.py", line 3, in
from .model import GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/model.py", line 17, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/init.py", line 1, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/renderer.py", line 6, in
import neural_renderer as nr
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/init.py", line 3, in
from .load_obj import load_obj
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/load_obj.py", line 8, in
import neural_renderer.cuda.load_textures as load_textures_cuda
ImportError: libcudart.so.9.2: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "run.py", line 7, in
from gan2shape import setup_runtime, Trainer, GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/init.py", line 3, in
from .model import GAN2Shape
File "/home/adminuser/GAN2Shape/gan2shape/model.py", line 17, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/init.py", line 1, in
from .renderer import Renderer
File "/home/adminuser/GAN2Shape/gan2shape/renderer/renderer.py", line 6, in
import neural_renderer as nr
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/init.py", line 3, in
from .load_obj import load_obj
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/neural_renderer/load_obj.py", line 8, in
import neural_renderer.cuda.load_textures as load_textures_cuda
ImportError: libcudart.so.9.2: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/torch/distributed/launch.py", line 235, in
main()
File "/home/adminuser/anaconda3/envs/test/lib/python3.6/site-packages/torch/distributed/launch.py", line 231, in main
cmd=process.args)
subprocess.CalledProcessError: Command '['/home/adminuser/anaconda3/envs/test/bin/python', '-u', 'run.py', '--local_rank=0', '--launcher', 'pytorch', '--config', 'configs/car.yml']' returned non-zero exit status 1.
additionally, pip install neural_renderer_pytorch StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback. StyleGAN2: Optimized CUDA op UpFirDn2d not available, using native PyTorch fallback. {'config': '/configs/car.yml', 'seed': 0, 'num_workers': 4, 'distributed': False} Setting up Perceptual loss... Downloading: "https://download.pytorch.org/models/vgg16-397923af.pth" to /root/.cache/torch/checkpoints/vgg16-397923af.pth 100% 528M/528M [00:03<00:00, 152MB/s] Loading model from: /content/drive/My Drive/GAN2Shape/gan2shape/stylegan2/stylegan2-pytorch/lpips/weights/v0.1/vgg.pth ...[net-lin [vgg]] initialized ...Done Traceback (most recent call last): File "run.py", line 31, in
trainer = Trainer(cfgs, GAN2Shape)
File "/content/drive/My Drive/GAN2Shape/gan2shape/trainer.py", line 23, in init
self.model = model(cfgs)
File "/content/drive/My Drive/GAN2Shape/gan2shape/model.py", line 98, in init
self.init_VL_sampler()
File "/content/drive/My Drive/GAN2Shape/gan2shape/model.py", line 346, in init_VL_sampler
light_mvn = torch.load(light_mvn_path)
File "/usr/local/lib/python3.6/site-packages/torch/serialization.py", line 381, in load
f = open(f, 'rb')
FileNotFoundError: [Errno 2] No such file or directory: 'checkpoints/view_light/view_light.pth'