junyanz / von Goto Github PK
View Code? Open in Web Editor NEW[NeurIPS 2018] Visual Object Networks: Image Generation with Disentangled 3D Representation.
Home Page: http://von.csail.mit.edu
License: Other
[NeurIPS 2018] Visual Object Networks: Image Generation with Disentangled 3D Representation.
Home Page: http://von.csail.mit.edu
License: Other
Hello,I have trouble in downloading your pretrained models and dataset.It's too slow.And I can not open your dropbox link.Can you provide Baidu SkyDrive link or some way easy to get in Chinese Mainland?Thank you!
Running into an error when feeding data into the model
I'm trying to train the model for top view car images, so after I downloaded the training data
However, I got the error below. Are there additional steps I'm missing in creating the training data?
Traceback (most recent call last):
File "train.py", line 22, in
for i, data in enumerate(dataset):
File "/media/marcchoo/Data/marcj/Documents/VON/data/init.py", line 84, in iter
for i, data in enumerate(self.dataloader):
File "/home/marcchoo/anaconda3/envs/von/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 336, in next
return self._process_next_batch(batch)
File "/home/marcchoo/anaconda3/envs/von/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 357, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
IndexError: Traceback (most recent call last):
File "/home/marcchoo/anaconda3/envs/von/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 106, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/marcchoo/anaconda3/envs/von/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 106, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/media/marcchoo/Data/marcj/Documents/VON/data/concat_dataset.py", line 9, in getitem
return tuple(d[i] for d in self.datasets)
File "/media/marcchoo/Data/marcj/Documents/VON/data/concat_dataset.py", line 9, in
return tuple(d[i] for d in self.datasets)
File "/media/marcchoo/Data/marcj/Documents/VON/data/images_dataset.py", line 95, in getitem
return self.get_item(index)
File "/media/marcchoo/Data/marcj/Documents/VON/data/images_dataset.py", line 115, in get_item
mask = im_out[3, :, :]
IndexError: index 3 is out of bounds for dimension 0 with size 3
Hi, I found it that during trianing, mult GPU didn't work.
For example
bash ./scripts/train_shape.sh 0,1 car df
only GPU 0 is working, the others only takes 10MB memory and 0% GPU Utility
| NVIDIA-SMI 390.67 Driver Version: 390.67 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 108... Off | 00000000:05:00.0 Off | N/A |
| 49% 82C P2 88W / 250W | 5849MiB / 11176MiB | 100% Default |
+-------------------------------+----------------------+----------------------+
| 1 GeForce GTX 108... Off | 00000000:06:00.0 Off | N/A |
| 26% 43C P8 9W / 250W | 10MiB / 11178MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
Thank you.
How can i train other objects? like ships ,animal.
Can you list the process of generating train data in detail?
Thank you very much
Hi,
Thank you for the code and the detailed installation procedure.
I needed some information on the training steps for the car use case.
We have the Quadro RTX 4000 GPU with 8 GB GDDR6 GPU memory. But on running the training for 2D texture network, it quickly uses up the memory and i have CUDA out of memory issue.
I kept reducing the dataset and finally was able to give only 10 images for training.
What was the hardware that you used for training and did you do any extra config for training 2605 images for the texture network?
Also can you suggest any steps to increase dataset without hitting the GPU memory issue.
I'm using PyTorch 0.4.1 with CUDA92 within conda
Thank you
In test.py, save_vox_to_obj(model.voxel.data.cpu().numpy(), 0.5 if not use_df else 0.85, obj_name)
. Why th parameter 'th' is 0.85 instead of 0.01 for default of ios_th.
def save_vox_to_obj(voxel, th, save_path): if len(voxel.shape) == 5: voxel_iso = voxel[0, 0, :, :, :] verts, faces, normals, values = measure.marching_cubes_lewiner(voxel_iso, th, spacing=(1 / 128, 1 / 128, 1 / 128),) save_obj(verts - 0.5, faces, save_path)
In the above usage, why verts - 0.5
?
Beacuse in test_shape.py,
v, f, n, _ = measure.marching_cubes_lewiner(output, opt.ios_th, spacing=(space, space, space)) save_obj(v, f, join(shape_dir, '%04d' % idx))
I wonder the difference for two cases. Thanks!
I met some problem when try to train VON,
Can you show me a easy example with sample and code? Thank you very much.
BTW, could you upload you data.tar to google drive or OneDrive? The link in your script is much too slow. Thank you very much again.
I've been trying to run the pipeline (only testing, no training) using a CPU only. Was this repository intended to do so?
In the readme it says that blender is optional and I interpreted it as blender being an alternative to the custom render module based on cuda. However, blender only seems to use whatever model.sample_2d() outputs and model.sample_2d() in turn is based on the custom render module.
Thanks in advance for commenting on this!
visualizing generated 3D shapes.
How to change the voxel value to distance function values?
What is the distance function you are actually using?
Could you elaborate how to change the shapenet file to your training data format?
Thanks a lot and waiting for your answer!
model.update_G()
model.update_D()
in standard GAN,
we need to update the parameter of D , then G.
1.I have successed in executing bash ./scripts/figures.sh 0
with df of car and chair. But when I try with voxel, it seems does have data. Your whole data is too big to download. Can you provide with a piece of data for test? The picture is for voxel of chair. It's same for voxel of car.
2.In executing bash ./scripts/test_shape.sh 0
with df and voxel, I did some adjustment. In test_shape.sh
. I remove epoch because of test. And is --th 0.012
for --ios_th 0.012
?
In test_shape.py
, I also made two adjuxtment,
# net_path = join(opt.checkpoints_dir, '%s_net_G_3D.pth' % opt.epoch) #改动 net_path = '/home/ljl/myproject/VON/final_models/models_3D/chair_df_G_3D.pth'
,
# result_root = join(opt.checkpoints_dir, 'test_epoch_%s' % opt.epoch) #改动 result_root = '/home/ljl/myproject/VON/results/test_shape_df_chair'
.
For the result, I have some questions. First, for df, the result of car has big holes in head and tail. Second, for voxel, it seems to be tattered.
I wander if I have something wrong in this.
3..In executing bash ./scripts/test_texture.sh 0
with df and voxel, I met same problem for voxel just as 1. And for df, I met this and I haven't figure it out.
It seems a lot.Thank you for your considering.
I just try figure.sh with RTX 2080ti +CUDA9.0+Pytorch0.4
Error occurs RuntimeError: cuda runtime error (11) : invalid argument at /opt/conda/conda-bld/pytorch_1532582628513/work/aten/src/THC/THCGeneral.cpp:663
RTX 2080ti +CUDA8.0+Pytorch0.4
Error occurs RuntimeError: CuDNN error: CUDNN_STATUS_EXECUTION_FAILED
RTX 2080ti + CUDA10+Pytorch 1.0
Error occurs cant find module 'vtn'
I am confused that does this job support RTX-GPUS?
When I train shapenet, the GPU utility is much too low, how to improve the training speed?
Hello, I can't find the usage of viewpoint code in your source code, I am not sure whether I ignore something, can you tell me about it? thank you.
Thank you so much for sharing your code. However, it seems that some of your scripts are missing. I cannot find CreateDataLoader
module. And there is no ./data
subfolder.
It shows
ModuleNotFoundError: No module named 'vtn'
However, the compilation succeeds. It only raises several WARNING but no errors in the compilation. And I run this code in the virtual env "von" initialized as the instruction.
bash install.sh
report error:cuda available but nvcc not found. Please add nvcc to $PATH.
I hope to create the df data of other resolutions, e.g. 64. But I do not find any code about this. Could you share the corresponding codes?
And here is a detail about data, I can't understand. It seems that there is no minus value in df data. So what do you save in voxel grids? I used to think they are signed distance function values.
hello,
when i ran "bash ./scripts/figures.sh 0 car df"
it occured errors:
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "test.py", line 19, in
model = create_model(opt)
File "/home/pf/VON/models/init.py", line 59, in create_model
instance = model(opt)
File "/home/pf/VON/models/test_model.py", line 34, in init
self.setup_DR(opt)
File "/home/pf/VON/models/base_model.py", line 159, in setup_DR
from render_module.render_sketch import VoxelRenderLayer, CroppingLayer, GetRotationMatrix, FineSizeCroppingLayer
File "/home/pf/VON/render_module/render_sketch.py", line 4, in
from vtn.vtn.functions import grid_sample3d, affine_grid3d
ModuleNotFoundError: No module named 'vtn'
i don not install render ,is this the reason?
Hi guys,
I am now trying to replicate the results on RTX 2080Ti. I added -gencode arch=compute_75,code=sm_75 to the nvcc command to make it work on RTX 2080Ti. I did the bash install and downloaded the models. It goes fine upto this step. Then when I run: bash ./scripts/figures.sh 0 car df, then I get the following error:
ImportError: /home/user/Downloads/VON/render_module/vtn/vtn/_ext/vtn_lib/_vtn_lib.so: undefined symbol: __cudaRegisterFatBinaryEnd
I see that the _vtn_lib.so is created there. Could you please point me in the right direction? Thank you.
Thanks for the great work with the great code.
I tried to use multi-GPU training recently, it seems that the training will down at the end of one epoch, as shown in the following picture
My script is as the following
python -u train.py --gpu_ids 0,1 --display_id 1000 --dataset_mode df --model 'shape_gan' --class_3d car --checkpoints_dir ${CHECKPOINTS_DIR} --niter 125 --niter_decay 125 --batch_size 16 --G_norm_3D inst3d --save_epoch_freq 10 --suffix {class_3d}_{model}_{dataset_mode}
My guess is that the training data has 3457 samples and 3457%16 = 1, thus at the last iteration, only one GPU got the sample while another one did not.
I am not sure whether the guess is right, so do you have any suggestions or solution to fix this bug?
I run into several strange error in compiling the code, could you kindly provide a dockerfile of your system environment please?
I'm trying to reproduce Generate 3d shape 2d sketch images part by
bash ./scripts/figures.sh 0 car df
below is the error
dataset [ImageAndDFDataset] was created
enable cudnn benchmark
initialization method [kaiming]
loading model from ./VON/scripts/../final_models/models_3D/car_df_G_3D.pth
initialization method [kaiming]
loading model from ./VON/scripts/../final_models/models_2D/car_df/latest_net_G_AB.pth
Traceback (most recent call last):
File "./VON/render_module/render_sketch.py", line 2, in <module>
from .vtn.vtn.functions import grid_sample3d, affine_grid3d
File "./VON/render_module/vtn/vtn/functions/__init__.py", line 2, in <module>
from .grid_sample3d import grid_sample3d
File "./VON/render_module/vtn/vtn/functions/grid_sample3d.py", line 3, in <module>
from .._ext import vtn_lib
ModuleNotFoundError: No module named 'render_module.vtn.vtn._ext'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "./test.py", line 19, in <module>
model = create_model(opt)
File "./VON/models/__init__.py", line 37, in create_model
instance.initialize(opt)
File "./VON/models/test_model.py", line 36, in initialize
self.setup_DR(opt)
File "./VON/models/base_model.py", line 161, in setup_DR
from render_module.render_sketch import VoxelRenderLayer, CroppingLayer, GetRotationMatrix, FineSizeCroppingLayer
File "./VON/render_module/render_sketch.py", line 4, in <module>
from vtn.vtn.functions import grid_sample3d, affine_grid3d
ModuleNotFoundError: No module named 'vtn'
it seems that there is no such file ./render_module/vtn/vtn/_ext.py
After sucessufully compiled ./install.sh
I tried to reproduceGenerate 3D shapes, 2.5D sketches, and images
part by runing bash ./scripts/figures.sh 0 car df
and got an error
error in BilinearSampler3D update output: no kernel image is available for execution on the device
BTW I can only find gcc 6.5
./install.sh
seems to be good./install.sh
Add -gencode to match all the GPU architectures you have.
Check 'https://en.wikipedia.org/wiki/CUDA#GPUs_supported' for list of architecture.
Check 'http://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html' for GPU compilation based on architecture.
nvcc -c -o vtn_cuda_kernel_generic.cu.o vtn_cuda_kernel_generic.cu -x cu -Xcompiler -fPIC -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/TH -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/THC -I /data/zhibo/codebase/VON/render_module/vtn/vtn/src -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_61,code=sm_61
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(114): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(232): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(114): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(232): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(114): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(232): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(114): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(232): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(114): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(232): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(114): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(232): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(114): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(232): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(114): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_kernel_generic.cu(232): warning: variable "index" was declared but never referenced
/data/zhibo/codebase/VON/render_module/vtn
Including CUDA code.
generating /tmp/tmpm4vcqi18/_vtn_lib.c
setting the current directory to '/tmp/tmpm4vcqi18'
running build_ext
building '_vtn_lib' extension
creating data
creating data/zhibo
creating data/zhibo/codebase
creating data/zhibo/codebase/VON
creating data/zhibo/codebase/VON/render_module
creating data/zhibo/codebase/VON/render_module/vtn
creating data/zhibo/codebase/VON/render_module/vtn/vtn
creating data/zhibo/codebase/VON/render_module/vtn/vtn/src
gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/data/zhibo/codebase/VON/render_module/vtn/vtn/src -I/home/zhibo/anaconda3/envs/von/include/python3.6m -c _vtn_lib.c -o ./_vtn_lib.o -std=c99 -fopenmp
gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/data/zhibo/codebase/VON/render_module/vtn/vtn/src -I/home/zhibo/anaconda3/envs/von/include/python3.6m -c /data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn.c -o ./data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn.o -std=c99 -fopenmp
gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/data/zhibo/codebase/VON/render_module/vtn/vtn/src -I/home/zhibo/anaconda3/envs/von/include/python3.6m -c /data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn_cuda_generic.c -o ./data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn_cuda_generic.o -std=c99 -fopenmp
gcc -pthread -shared -L/home/zhibo/anaconda3/envs/von/lib -Wl,-rpath=/home/zhibo/anaconda3/envs/von/lib,--no-as-needed -L/home/zhibo/anaconda3/envs/von/lib -Wl,-rpath=/home/zhibo/anaconda3/envs/von/lib,--no-as-needed ./_vtn_lib.o ./data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn.o ./data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn_cuda_generic.o /data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn_cuda_kernel_generic.cu.o -L/home/zhibo/anaconda3/envs/von/lib -lpython3.6m -o ./_vtn_lib.so
Add -gencode to match all the GPU architectures you have.
Check 'https://en.wikipedia.org/wiki/CUDA#GPUs_supported' for list of architecture.
Check 'http://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html' for GPU compilation based on architecture.
nvcc -c -o calc_prob_kernel.cu.o calc_prob_kernel.cu -x cu -Xcompiler -fPIC -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/TH -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/THC -I /data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70
/data/zhibo/codebase/VON/render_module/calc_prob
generating /tmp/tmpvho7ta2j/_calc_prob_lib.c
setting the current directory to '/tmp/tmpvho7ta2j'
running build_ext
building '_calc_prob_lib' extension
creating data
creating data/zhibo
creating data/zhibo/codebase
creating data/zhibo/codebase/VON
creating data/zhibo/codebase/VON/render_module
creating data/zhibo/codebase/VON/render_module/calc_prob
creating data/zhibo/codebase/VON/render_module/calc_prob/calc_prob
creating data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src
gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA=True -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src -I/home/zhibo/anaconda3/envs/von/include/python3.6m -c _calc_prob_lib.c -o ./_calc_prob_lib.o -std=c99
gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA=True -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src -I/home/zhibo/anaconda3/envs/von/include/python3.6m -c /data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src/calc_prob.c -o ./data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src/calc_prob.o -std=c99
gcc -pthread -shared -L/home/zhibo/anaconda3/envs/von/lib -Wl,-rpath=/home/zhibo/anaconda3/envs/von/lib,--no-as-needed -L/home/zhibo/anaconda3/envs/von/lib -Wl,-rpath=/home/zhibo/anaconda3/envs/von/lib,--no-as-needed ./_calc_prob_lib.o ./data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src/calc_prob.o /data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src/calc_prob_kernel.cu.o -L/home/zhibo/anaconda3/envs/von/lib -lpython3.6m -o ./_calc_prob_lib.so
bash ./scripts/figures.sh 0 car df
+ GPU_ID=0
+ CLASS=car
+ DATASET=df
+++ dirname ./scripts/figures.sh
++ cd ./scripts
++ pwd -P
+ SCRIPTPATH=/data/zhibo/codebase/VON/scripts
+ ROOT_DIR=/data/zhibo/codebase/VON/scripts/..
+ DISPLAY_ID=1
+ MODEL2D_DIR=/data/zhibo/codebase/VON/scripts/../final_models/models_2D/car_df/latest
+ MODEL3D_DIR=/data/zhibo/codebase/VON/scripts/../final_models/models_3D/car_df
+ RESULTS_DIR=/data/zhibo/codebase/VON/scripts/../results/fig_car_df/
+ NUM_SHAPES=20
+ NUM_SAMPLES=5
+ CUDA_VISIBLE_DEVICES=0
+ python ./test.py --results_dir /data/zhibo/codebase/VON/scripts/../results/fig_car_df/ --model2D_dir /data/zhibo/codebase/VON/scripts/../final_models/models_2D/car_df/latest --model3D_dir /data/zhibo/codebase/VON/scripts/../final_models/models_3D/car_df --class_3d car --phase val --dataset_mode image_and_df --model test --n_shapes 20 --n_views 5 --reset_texture --reset_shape --suffix car_df --batch_size 1 --use_df
----------------- Options ---------------
D_norm_3D: none
G_norm_3D: batch3d
aspect_ratio: 1.0
batch_size: 1 [default: 12]
checkpoints_dir: ../../results_texture/
class_3d: car
color_jitter: False
crop_align: False
dataroot: None
dataset_mode: image_and_df [default: base]
df_flipped: False
df_sigma: 8.0
df_th: 0.9
display_winsize: 128
epoch: latest
fine_size: 128
gan_mode: lsgan
gpu_ids: 0
init_param: 0.02
init_type: kaiming
input_nc: 1
interp_shape: False
interp_texture: False
isTrain: False [default: None]
load_size: 128
max_dataset_size: inf
model: test [default: stage]
model2D_dir: /data/zhibo/codebase/VON/scripts/../final_models/models_2D/car_df/latest [default: None]
model3D_dir: /data/zhibo/codebase/VON/scripts/../final_models/models_3D/car_df [default: None]
n_shapes: 20 [default: 10]
n_views: 5 [default: 10]
name: car_df [default: experiment_name]
ndf: 64
ndf_3d: 64
nef: 64
netD: multi
netD_3D: D0
netE: adaIN
netG: resnet_cat
netG_3D: G0
ngf: 64
ngf_3d: 64
nl: relu
no_flip: False
no_largest: False
norm: inst
num_Ds: 2
num_threads: 6
nz_shape: 200
nz_texture: 8
output_nc: 3
phase: val
pose_align: False
pose_type: hack
print_grad: False
random_shift: False
random_view: False
real_shape: False
real_texture: False
render_25d: False
render_3d: False
reset_shape: True [default: False]
reset_texture: True [default: False]
resize_or_crop: crop_real_im
results_dir: /data/zhibo/codebase/VON/scripts/../results/fig_car_df/ [default: ../results/]
seed: 0
serial_batches: False
show_input: False
show_rec: False
suffix: car_df [default: ]
th: 0.01
use_df: True [default: False]
use_dropout: False
verbose: False
voxel_res: 128
where_add: all
----------------- End -------------------
dataset [ImageAndDFDataset] was created
enable cudnn benchmark
initialization method [kaiming]
loading model from /data/zhibo/codebase/VON/scripts/../final_models/models_3D/car_df_G_3D.pth
initialization method [kaiming]
loading model from /data/zhibo/codebase/VON/scripts/../final_models/models_2D/car_df/latest_net_G_AB.pth
initialization method [kaiming]
loading model from /data/zhibo/codebase/VON/scripts/../final_models/models_2D/car_df/latest_net_E.pth
model [TestModel] was created
---------- Networks -------------
[G_AB] Total #parameters : 8.924 M
[G_3D] Total #parameters : 17.832 M
[E] Total #parameters : 1.718 M
-----------------------------------------------
Loading model test
creating website /data/zhibo/codebase/VON/scripts/../results/fig_car_df/car_df_views5_shape20_rFalse
0%| | 0/20 [00:00<?, ?it/s]
error in BilinearSampler3D update output: no kernel image is available for execution on the device
Exception ignored in: <bound method _DataLoaderIter.__del__ of <torch.utils.data.dataloader._DataLoaderIter object at 0x7fba3b1fcfd0>>
Traceback (most recent call last):
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 399, in __del__
self._shutdown_workers()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 378, in _shutdown_workers
self.worker_result_queue.get()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/multiprocessing/queues.py", line 337, in get
return _ForkingPickler.loads(res)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/multiprocessing/reductions.py", line 151, in rebuild_storage_fd
fd = df.detach()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/multiprocessing/resource_sharer.py", line 58, in detach
return reduction.recv_handle(conn)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/multiprocessing/reduction.py", line 182, in recv_handle
return recvfds(s, 1)[0]
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/multiprocessing/reduction.py", line 153, in recvfds
msg, ancdata, flags, addr = sock.recvmsg(1, socket.CMSG_SPACE(bytes_size))
ConnectionResetError: [Errno 104] Connection reset by peer
Traceback (most recent call last):
File "./test.py", line 61, in <module>
image, depth, mask = model.sample_2d(view_id=k, extra=True)
File "/data/zhibo/codebase/VON/models/test_model.py", line 119, in sample_2d
self.mask, self.depth = self.get_depth(self.voxel, self.rot_mat, use_df=self.use_df)
File "/data/zhibo/codebase/VON/models/base_model.py", line 271, in get_depth
silhouette_orig, depth_orig = self.renderLayer(voxel, rot_mat)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
result = self.forward(*input, **kwargs)
File "/data/zhibo/codebase/VON/render_module/render_sketch.py", line 249, in forward
voxel_rot = self.grid_sampler3d(voxel_in, voxel_rot_grid)
File "/data/zhibo/codebase/VON/render_module/vtn/vtn/functions/grid_sample3d.py", line 62, in grid_sample3d
return GridSampler3D.apply(input, grid)
File "/data/zhibo/codebase/VON/render_module/vtn/vtn/functions/grid_sample3d.py", line 35, in forward
getattr(vtn_lib, func_name)(input, grid, output)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/__init__.py", line 202, in safe_call
result = torch._C._safe_call(*args, **kwargs)
torch.FatalError: aborting at /data/zhibo/codebase/VON/render_module/vtn/vtn/src/generic/vtn_cuda_generic.c:15
I tried to run ./install.sh
Add -gencode to match all the GPU architectures you have.
Check 'https://en.wikipedia.org/wiki/CUDA#GPUs_supported' for list of architecture.
Check 'http://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html' for GPU compilation based on architecture.
nvcc -c -o vtn_cuda_kernel_generic.cu.o vtn_cuda_kernel_generic.cu -x cu -Xcompiler -fPIC -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/TH -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/THC -I /data/zhibo/codebase/VON/render_module/vtn/vtn/src -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_61,code=sm_61
In file included from /usr/include/c++/5/type_traits:35:0,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/ATen/optional.h:19,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/ATen/Error.h:4,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/ATen/Allocator.h:6,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/TH/THAllocator.h:6,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/THC/THCGeneral.h:5,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/THC/THC.h:4,
from vtn_cuda_kernel_generic.cu:1:
/usr/include/c++/5/bits/c++0x_warning.h:32:2: error: #error This file requires compiler and library support for the ISO C++ 2011 standard. This support must be enabled with the -std=c++11 or -std=gnu++11 compiler options.
#error This file requires compiler and library support \
^
/data/zhibo/codebase/VON/render_module/vtn
Including CUDA code.
generating /tmp/tmpeiqqa8a6/_vtn_lib.c
setting the current directory to '/tmp/tmpeiqqa8a6'
running build_ext
building '_vtn_lib' extension
creating data
creating data/zhibo
creating data/zhibo/codebase
creating data/zhibo/codebase/VON
creating data/zhibo/codebase/VON/render_module
creating data/zhibo/codebase/VON/render_module/vtn
creating data/zhibo/codebase/VON/render_module/vtn/vtn
creating data/zhibo/codebase/VON/render_module/vtn/vtn/src
gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/data/zhibo/codebase/VON/render_module/vtn/vtn/src -I/home/zhibo/anaconda3/envs/von/include/python3.6m -c _vtn_lib.c -o ./_vtn_lib.o -std=c99 -fopenmp
gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/data/zhibo/codebase/VON/render_module/vtn/vtn/src -I/home/zhibo/anaconda3/envs/von/include/python3.6m -c /data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn.c -o ./data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn.o -std=c99 -fopenmp
gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/data/zhibo/codebase/VON/render_module/vtn/vtn/src -I/home/zhibo/anaconda3/envs/von/include/python3.6m -c /data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn_cuda_generic.c -o ./data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn_cuda_generic.o -std=c99 -fopenmp
gcc -pthread -shared -L/home/zhibo/anaconda3/envs/von/lib -Wl,-rpath=/home/zhibo/anaconda3/envs/von/lib,--no-as-needed -L/home/zhibo/anaconda3/envs/von/lib -Wl,-rpath=/home/zhibo/anaconda3/envs/von/lib,--no-as-needed ./_vtn_lib.o ./data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn.o ./data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn_cuda_generic.o /data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn_cuda_kernel_generic.cu.o -L/home/zhibo/anaconda3/envs/von/lib -lpython3.6m -o ./_vtn_lib.so
gcc: error: /data/zhibo/codebase/VON/render_module/vtn/vtn/src/vtn_cuda_kernel_generic.cu.o: No such file or directory
Traceback (most recent call last):
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/unixccompiler.py", line 196, in link
self.spawn(linker + ld_args)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/ccompiler.py", line 909, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/spawn.py", line 159, in _spawn_posix
% (cmd, exit_status))
distutils.errors.DistutilsExecError: command 'gcc' failed with exit status 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/cffi/ffiplatform.py", line 51, in _build
dist.run_command('build_ext')
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/command/build_ext.py", line 448, in build_extensions
self._build_extensions_serial()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/command/build_ext.py", line 473, in _build_extensions_serial
self.build_extension(ext)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/command/build_ext.py", line 558, in build_extension
target_lang=language)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/ccompiler.py", line 717, in link_shared_object
extra_preargs, extra_postargs, build_temp, target_lang)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/unixccompiler.py", line 198, in link
raise LinkError(msg)
distutils.errors.LinkError: command 'gcc' failed with exit status 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "build.py", line 52, in <module>
ffi.build()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/__init__.py", line 189, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/__init__.py", line 111, in _build_extension
outfile = ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.__class__.__name__, e))
cffi.error.VerificationError: LinkError: command 'gcc' failed with exit status 1
Add -gencode to match all the GPU architectures you have.
Check 'https://en.wikipedia.org/wiki/CUDA#GPUs_supported' for list of architecture.
Check 'http://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html' for GPU compilation based on architecture.
nvcc -c -o calc_prob_kernel.cu.o calc_prob_kernel.cu -x cu -Xcompiler -fPIC -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/TH -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include -I /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/THC -I /data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70
In file included from /usr/include/c++/5/type_traits:35:0,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/ATen/optional.h:19,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/ATen/Error.h:4,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/ATen/Allocator.h:6,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/TH/THAllocator.h:6,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/THC/THCGeneral.h:5,
from /home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/lib/include/THC/THC.h:4,
from calc_prob_kernel.cu:1:
/usr/include/c++/5/bits/c++0x_warning.h:32:2: error: #error This file requires compiler and library support for the ISO C++ 2011 standard. This support must be enabled with the -std=c++11 or -std=gnu++11 compiler options.
#error This file requires compiler and library support \
^
/data/zhibo/codebase/VON/render_module/calc_prob
generating /tmp/tmpti_xa_36/_calc_prob_lib.c
setting the current directory to '/tmp/tmpti_xa_36'
running build_ext
building '_calc_prob_lib' extension
creating data
creating data/zhibo
creating data/zhibo/codebase
creating data/zhibo/codebase/VON
creating data/zhibo/codebase/VON/render_module
creating data/zhibo/codebase/VON/render_module/calc_prob
creating data/zhibo/codebase/VON/render_module/calc_prob/calc_prob
creating data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src
gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA=True -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src -I/home/zhibo/anaconda3/envs/von/include/python3.6m -c _calc_prob_lib.c -o ./_calc_prob_lib.o -std=c99
gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA=True -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src -I/home/zhibo/anaconda3/envs/von/include/python3.6m -c /data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src/calc_prob.c -o ./data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src/calc_prob.o -std=c99
gcc -pthread -shared -L/home/zhibo/anaconda3/envs/von/lib -Wl,-rpath=/home/zhibo/anaconda3/envs/von/lib,--no-as-needed -L/home/zhibo/anaconda3/envs/von/lib -Wl,-rpath=/home/zhibo/anaconda3/envs/von/lib,--no-as-needed ./_calc_prob_lib.o ./data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src/calc_prob.o /data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src/calc_prob_kernel.cu.o -L/home/zhibo/anaconda3/envs/von/lib -lpython3.6m -o ./_calc_prob_lib.so
gcc: error: /data/zhibo/codebase/VON/render_module/calc_prob/calc_prob/src/calc_prob_kernel.cu.o: No such file or directory
Traceback (most recent call last):
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/unixccompiler.py", line 196, in link
self.spawn(linker + ld_args)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/ccompiler.py", line 909, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/spawn.py", line 159, in _spawn_posix
% (cmd, exit_status))
distutils.errors.DistutilsExecError: command 'gcc' failed with exit status 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/cffi/ffiplatform.py", line 51, in _build
dist.run_command('build_ext')
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/command/build_ext.py", line 448, in build_extensions
self._build_extensions_serial()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/command/build_ext.py", line 473, in _build_extensions_serial
self.build_extension(ext)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/command/build_ext.py", line 558, in build_extension
target_lang=language)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/ccompiler.py", line 717, in link_shared_object
extra_preargs, extra_postargs, build_temp, target_lang)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/distutils/unixccompiler.py", line 198, in link
raise LinkError(msg)
distutils.errors.LinkError: command 'gcc' failed with exit status 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "build.py", line 42, in <module>
ffi.build()
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/__init__.py", line 189, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/torch/utils/ffi/__init__.py", line 111, in _build_extension
outfile = ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/home/zhibo/anaconda3/envs/von/lib/python3.6/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.__class__.__name__, e))
cffi.error.VerificationError: LinkError: command 'gcc' failed with exit status 1
Thanks to your awesome work! Generating images from 3D is a great idea!
You demonstrated some images of distance function grids in your paper, but there seems no code doing this, sorry I'm new to 3D learning.
I‘m wondering how to get distance functions from a mesh like *.obj files, and how to render such a N x N x N distance grid in 3D view (just like your paper). Can you provide some tools or just tell me the name?
Add -gencode to match all the GPU architectures you have.
Check 'https://en.wikipedia.org/wiki/CUDA#GPUs_supported' for list of architecture.
Check 'http://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html' for GPU compilation based on architecture.
nvcc -c -o vtn_cuda_kernel_generic.cu.o vtn_cuda_kernel_generic.cu -x cu -Xcompiler -fPIC -std=c++11 -I /usr/local/anaconda3/lib/python3.7/site-packages/torch/lib/include/TH -I /usr/local/anaconda3/lib/python3.7/site-packages/torch/lib/include -I /usr/local/anaconda3/lib/python3.7/site-packages/torch/lib/include/THC -I /home/humaolin/papercode/VON/render_module/vtn/vtn/src -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_61,code=sm_61
vtn_cuda_kernel_generic.cu:1:10: fatal error: THC.h: No such file or directory
#include <THC.h>
^~~~~~~
compilation terminated.
I followed the steps in README.md, but got errors when I use this command:
bash install.sh
The errors are as follows:
gcc: error:/home/asd/VON/render_module/vtn/vtn/src/vtn_cuda_kernel_generic.cu.o:No such file or directory
Traceback (most recent call last):
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/unixccompiler.py", line 197, in link
self.spawn(linker + ld_args)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/ccompiler.py", line 909, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/spawn.py", line 159, in _spawn_posix
% (cmd, exit_status))
distutils.errors.DistutilsExecError: command 'gcc' failed with exit status 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/cffi/ffiplatform.py", line 51, in _build
dist.run_command('build_ext')
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/command/build_ext.py", line 448, in build_extensions
self._build_extensions_serial()
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/command/build_ext.py", line 473, in _build_extensions_serial
self.build_extension(ext)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/command/build_ext.py", line 558, in build_extension
target_lang=language)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/ccompiler.py", line 717, in link_shared_object
extra_preargs, extra_postargs, build_temp, target_lang)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/unixccompiler.py", line 199, in link
raise LinkError(msg)
distutils.errors.LinkError: command 'gcc' failed with exit status 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "build.py", line 52, in <module>
ffi.build()
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/utils/ffi/__init__.py", line 189, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/utils/ffi/__init__.py", line 111, in _build_extension
outfile = ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.__class__.__name__, e))
cffi.error.VerificationError: LinkError: command 'gcc' failed with exit status 1
Add -gencode to match all the GPU architectures you have.
Check 'https://en.wikipedia.org/wiki/CUDA#GPUs_supported' for list of architecture.
Check 'http://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html' for GPU compilation based on architecture.
nvcc -c -o calc_prob_kernel.cu.o calc_prob_kernel.cu -x cu -Xcompiler -fPIC -I /home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/lib/include/TH -I /home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/lib/include -I /home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/lib/include/THC -I /home/asd/VON/render_module/calc_prob/calc_prob/src -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70
nvcc fatal : Unsupported gpu architecture 'compute_61'
/home/asd/VON/render_module/calc_prob
generating /tmp/tmpje48npiy/_calc_prob_lib.c
setting the current directory to '/tmp/tmpje48npiy'
running build_ext
building '_calc_prob_lib' extension
creating home
creating home/asd
creating home/asd/VON
creating home/asd/VON/render_module
creating home/asd/VON/render_module/calc_prob
creating home/asd/VON/render_module/calc_prob/calc_prob
creating home/asd/VON/render_module/calc_prob/calc_prob/src
gcc -pthread -B /home/asd/anaconda3/envs/tang/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA=True -I/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/home/asd/VON/render_module/calc_prob/calc_prob/src -I/home/asd/anaconda3/envs/tang/include/python3.6m -c _calc_prob_lib.c -o ./_calc_prob_lib.o -std=c99
gcc -pthread -B /home/asd/anaconda3/envs/tang/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA=True -I/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/home/asd/VON/render_module/calc_prob/calc_prob/src -I/home/asd/anaconda3/envs/tang/include/python3.6m -c /home/asd/VON/render_module/calc_prob/calc_prob/src/calc_prob.c -o ./home/asd/VON/render_module/calc_prob/calc_prob/src/calc_prob.o -std=c99
gcc -pthread -shared -B /home/asd/anaconda3/envs/tang/compiler_compat -L/home/asd/anaconda3/envs/tang/lib -Wl,-rpath=/home/asd/anaconda3/envs/tang/lib -Wl,--no-as-needed -Wl,--sysroot=/ ./_calc_prob_lib.o ./home/asd/VON/render_module/calc_prob/calc_prob/src/calc_prob.o /home/asd/VON/render_module/calc_prob/calc_prob/src/calc_prob_kernel.cu.o -o ./_calc_prob_lib.so
gcc: error:/home/asd/VON/render_module/calc_prob/calc_prob/src/calc_prob_kernel.cu.o:No such file or directory
Traceback (most recent call last):
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/unixccompiler.py", line 197, in link
self.spawn(linker + ld_args)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/ccompiler.py", line 909, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/spawn.py", line 159, in _spawn_posix
% (cmd, exit_status))
distutils.errors.DistutilsExecError: command 'gcc' failed with exit status 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/cffi/ffiplatform.py", line 51, in _build
dist.run_command('build_ext')
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/command/build_ext.py", line 448, in build_extensions
self._build_extensions_serial()
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/command/build_ext.py", line 473, in _build_extensions_serial
self.build_extension(ext)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/command/build_ext.py", line 558, in build_extension
target_lang=language)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/ccompiler.py", line 717, in link_shared_object
extra_preargs, extra_postargs, build_temp, target_lang)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/distutils/unixccompiler.py", line 199, in link
raise LinkError(msg)
distutils.errors.LinkError: command 'gcc' failed with exit status 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "build.py", line 42, in <module>
ffi.build()
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/utils/ffi/__init__.py", line 189, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/torch/utils/ffi/__init__.py", line 111, in _build_extension
outfile = ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/home/asd/anaconda3/envs/tang/lib/python3.6/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.__class__.__name__, e))
cffi.error.VerificationError: LinkError: command 'gcc' failed with exit status 1
The code seems hard to understand with complex structure, any guide please?
For example, where is the network architecture definition?
I downloaded the model using bash ./scripts/download_model.sh
.
But then when I try
bash ./scripts/figures.sh 0 car df
to generate samples, I get the following output.
+ GPU_ID=0
+ CLASS=car
+ DATASET=df
+++ dirname ./scripts/figures.sh
++ cd ./scripts
++ pwd -P
+ SCRIPTPATH=/om/user/ilkery/VON/scripts
+ ROOT_DIR=/om/user/ilkery/VON/scripts/.. [72/1761]
+ DISPLAY_ID=1
+ MODEL2D_DIR=/om/user/ilkery/VON/scripts/../final_models/models_2D/car_df/latest
+ MODEL3D_DIR=/om/user/ilkery/VON/scripts/../final_models/models_3D/car_df
+ RESULTS_DIR=/om/user/ilkery/VON/scripts/../results/fig_car_df/
+ NUM_SHAPES=20
+ NUM_SAMPLES=5
+ CUDA_VISIBLE_DEVICES=0
+ python ./test.py --results_dir /om/user/ilkery/VON/scripts/../results/fig_car_df/ --model2D_dir /om/user/ilkery/VON/scripts/../final_models/models_2D/car_df/latest --model3D_dir /
om/user/ilkery/VON/scripts/../final_models/models_3D/car_df --class_3d car --phase val --dataset_mode image_and_df --model test --n_shapes 20 --n_views 5 --reset_texture --reset_sha
pe --suffix car_df --batch_size 1 --use_df
----------------- Options ---------------
D_norm_3D: none
G_norm_3D: batch3d
aspect_ratio: 1.0
batch_size: 1 [default: 12]
checkpoints_dir: ../../results_texture/
class_3d: car
color_jitter: False
crop_align: False
dataroot: None
dataset_mode: image_and_df [default: base]
df_flipped: False
df_sigma: 8.0
df_th: 0.9
display_winsize: 128
epoch: latest
fine_size: 128
gan_mode: lsgan
gpu_ids: 0
init_param: 0.02
init_type: kaiming
input_nc: 1
interp_shape: False
interp_texture: False
isTrain: False [default: None]
load_size: 128 [36/1761]
max_dataset_size: inf
model: test [default: stage]
model2D_dir: /om/user/ilkery/VON/scripts/../final_models/models_2D/car_df/latest [default: None]
model3D_dir: /om/user/ilkery/VON/scripts/../final_models/models_3D/car_df [default: None]
n_shapes: 20 [default: 10]
n_views: 5 [default: 10]
name: car_df [default: experiment_name]
ndf: 64
ndf_3d: 64
nef: 64
netD: multi
netD_3D: D0
netE: adaIN
netG: resnet_cat
netG_3D: G0
ngf: 64
ngf_3d: 64
nl: relu
no_flip: False
no_largest: False
norm: inst
num_Ds: 2
num_threads: 6
nz_shape: 200
nz_texture: 8
output_nc: 3
phase: val
pose_align: False
pose_type: hack
print_grad: False
random_shift: False
random_view: False
real_shape: False
real_texture: False
render_25d: False
render_3d: False
reset_shape: True [default: False]
reset_texture: True [default: False]
resize_or_crop: crop_real_im
results_dir: /om/user/ilkery/VON/scripts/../results/fig_car_df/ [default: ../results/]
seed: 0
serial_batches: False
show_input: False
show_rec: False
suffix: car_df [default: ]
th: 0.01
use_df: True [default: False]
use_dropout: False
verbose: False
voxel_res: 128
where_add: all
----------------- End -------------------
dataset [ImageAndDFDataset] was created
enable cudnn benchmark
initialization method [kaiming]
loading model from /om/user/ilkery/VON/scripts/../final_models/models_3D/car_df_G_3D.pth
Traceback (most recent call last):
File "./test.py", line 19, in <module>
model = create_model(opt)
File "/om/user/ilkery/VON/models/__init__.py", line 37, in create_model
instance.initialize(opt)
File "/om/user/ilkery/VON/models/test_model.py", line 28, in initialize
self.netG_3D = self.define_G_3D()
File "/om/user/ilkery/VON/models/base_model.py", line 68, in define_G_3D
self.load_network(netG, opt.model3D_dir + '_G_3D.pth')
File "/om/user/ilkery/VON/models/base_model.py", line 142, in load_network
net.module.load_state_dict(torch.load(path))
File "/om/user/ilkery/envs/pytorch_v04/lib/python3.6/site-packages/torch/nn/modules/module.py", line 721, in load_state_dict
self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for _netG0:
Unexpected key(s) in state_dict: "block_0.1.num_batches_tracked", "block_1.1.num_batches_tracked", "block_2.1.num_batches_tracked", "block_3.1.num_batches_tracked", "block_4.1.num_batches_tracked".
I can not find your supplemental material neither on the project page nor on NIPS page? Where else can I refer to?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.