Comments (9)
@zhuhaozh the segmentation fault is caused by the flownet2-pytorch dependency in this model. Which required pytorch 0.4.1. I suggest that you use docker. Here is my dockerfile that works I hope it helps.
FROM nvidia/cuda:10.1-cudnn7-devel-ubuntu16.04
RUN apt-get update && apt-get install -y \
curl \
ca-certificates \
sudo \
git \
bzip2 \
libx11-6 \
build-essential \
&& rm -rf /var/lib/apt/lists/*
# Create a working directory
RUN mkdir /app
WORKDIR /app
# Create a non-root user and switch to it
RUN adduser --disabled-password --gecos '' --shell /bin/bash user \
&& chown -R user:user /app
RUN echo "user ALL=(ALL) NOPASSWD:ALL" > /etc/sudoers.d/90-user
USER user
# All users can use /home/user as their home directory
ENV HOME=/home/user
RUN chmod 777 /home/user
# Install Miniconda
RUN curl -so ~/miniconda.sh https://repo.continuum.io/miniconda/Miniconda3-4.5.11-Linux-x86_64.sh \
&& chmod +x ~/miniconda.sh \
&& ~/miniconda.sh -b -p ~/miniconda \
&& rm ~/miniconda.sh
ENV PATH=/home/user/miniconda/bin:$PATH
ENV CONDA_AUTO_UPDATE_CONDA=false
# Create a Python 3.6 environment
RUN /home/user/miniconda/bin/conda create -y --name py36 python=3.6.9 \
&& /home/user/miniconda/bin/conda clean -ya
ENV CONDA_DEFAULT_ENV=py36
ENV CONDA_PREFIX=/home/user/miniconda/envs/$CONDA_DEFAULT_ENV
ENV PATH=$CONDA_PREFIX/bin:$PATH
RUN /home/user/miniconda/bin/conda install conda-build=3.18.9=py36_3 \
&& /home/user/miniconda/bin/conda clean -ya
RUN conda install -y -c pytorch pytorch=1.3.1 torchvision=0.4.2 \
&& conda clean -ya
# Install HDF5 Python bindings
RUN conda install -y h5py=2.8.0 \
&& conda clean -ya
RUN pip install h5py-cache==1.0
# Install Torchnet, a high-level framework for PyTorch
RUN pip install torchnet==0.0.4
# Install Requests, a Python library for making HTTP requests
RUN conda install -y requests=2.19.1
# Install Graphviz
RUN conda install -y graphviz=2.40.1 python-graphviz=0.8.4
# Install Scikit Image
RUN conda install -y -c anaconda scikit-image
# Install OpenCV3 Python bindings
RUN sudo apt-get update && sudo apt-get install -y --no-install-recommends \
libgtk2.0-0 \
libcanberra-gtk-module \
&& sudo rm -rf /var/lib/apt/lists/*
RUN conda install -y -c conda-forge opencv dominate dlib pillow=6.1 \
&& conda clean -ya
RUN git clone https://github.com/NVlabs/few-shot-vid2vid
WORKDIR /app/few-shot-vid2vid/
RUN python scripts/download_datasets.py
# Set the default command to bash
CMD ["/bin/bash"]
from few-shot-vid2vid.
It does work with pytorch 1.1.0
from few-shot-vid2vid.
Hi, @nfrik
I use pytorch1.1.0, but encountered the segment fault. I cannot install pytorch1.2.0 on the server... so, i don't know whether it is caused by the version of pytorch
from few-shot-vid2vid.
Hi, @zhuhaozh
Can you use docker?
from few-shot-vid2vid.
Hi, @nfrik
I use pytorch1.1.0, but encountered the segment fault. I cannot install pytorch1.2.0 on the server... so, i don't know whether it is caused by the version of pytorch
I doubt that segmentation fault is caused by pytorch version. There could be many factors causing that, but you might need to upgrade/downgrade your numpy version. Also try to rerun your code, since each time generator is initialized with random state.
from few-shot-vid2vid.
Thanks, I will try it later.
from few-shot-vid2vid.
@hamzatrq Thanks for your Dockerfile! But which version of Pillow you are using?
I'm getting "ImportError: cannot import name 'PILLOW_VERSION'"
from few-shot-vid2vid.
Pillow is updated to version 7, but we need version 6. Please run:
$ conda install pillow=6.1
Also updated the dockerfile above.
from few-shot-vid2vid.
Thanks, @hamzatrq! Can you also share docker-compose.yml
with us? I have not used Docker before, but the document indicates that we'll also need that file to define an environment.
from few-shot-vid2vid.
Related Issues (20)
- "dance" and "talking head" pretrained model requests HOT 1
- [face] image's background shaking HOT 1
- [street] Totally black output on epoch 1 HOT 4
- Segmentation fault HOT 1
- Have an error when using tensorboard
- Youtube playlist 3 - Pose model HOT 1
- [face]Is the training result normal? HOT 2
- faceforensics dataset download HOT 1
- Generating multiple person from poses
- Did any one successfully trained any model?. If yes how long does it take?.. HOT 1
- error in download_youTube_playlist.py HOT 2
- GTC 2021 animated video HOT 2
- fsVid2Vid--ZeroDivisionError: float division by zero
- Train getting NoneType for input to forward during train
- Regarding crop_coords
- What are the best configurations to run the "few-shot-vid2vid" model HOT 2
- hi, @yashasbharadwaj111 HOT 1
- 0 sequences HOT 2
- question about training model
- vid2video,which rep is the best in 2024,this year
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from few-shot-vid2vid.