Comments (4)
ok, so I tried running the code with pytorch v1.1 and it failed.
Now, I have setup a new virtual env for your project only, where I did install pytorch 1.0.0. I am going through t)the dependencies installation currently (there are many dependencies you did not list in your readme but I can figure out hopefully.
So I am reaching the torchvision dependency (ModuleNotFoundError: No module named 'torchvision'), then I am like doing pip3 install torchvision but then it tries to install pytoch1.2.
So I kill it and I am trying to prevent this, but on the pypi webpage of torchvision (https://pypi.org/project/torchvision/) they say "TorchVision requires PyTorch 1.1 or newer."
So your project requires pytorch <=1.0.0 but your project has a dependency on torchvision which itself requires pytorch v1.1 or above... please help me resolve this indefinite loop!!!
thanks a lot
from gscnn.
I was able to install torch vision by forcing it to use torchvision==0.2.0. I'm not sure if it's the right thing to do or not, but as you mentioned installing torchvision by default upgrades torch to 1.2.0.
from gscnn.
Thanks for your interest in our work! As mentioned in #6, the PyTorch versioning was a typo and I have now amended it. Using the newest versions for most things should in theory work, although you may need to make certain tweaks if there are deprecated functions etc. I can try to find out which exact versions I used for the dependencies.
from gscnn.
Thanks a lot for your help and clarifications. Great project. Closing this.
from gscnn.
Related Issues (20)
- How to use the argument 'trunk' and the backbone 'resnet18'?
- DualTaskLoss not working HOT 4
- ede
- Change the picture test method
- from network.wider_resnet import wider_resnet38_a2 HOT 3
- Error in DualTaskLoss while running the evaluation HOT 1
- TypeError: resolve_type_from_object()
- gate about reset
- Typo in gradient_central_diff in custom_functional.py
- How to test with single image?
- the computer crashed und rebooted after training for a while HOT 1
- result is not very good HOT 2
- ValueError: batch_size should be a positive integer value, but got batch_size=0
- Segment single image using saved model HOT 4
- ImportError: No module named 'enclib_cpu'
- ModuleNotFoundError: No module named 'encoding' HOT 2
- このコードの構造は本当に改善する必要があります
- 07-07 16:49:07.175 NaN or Inf found in input tensor.
- Question about Dual Task Loss notation in the paper
- THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=383 error=8 : invalid device function
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 gscnn.