Comments (11)
padding is eaten away and replaced by .padW and .padH
from cunn.
from cunn.
OK, but I get the error. How can I forward the image successfully?
The error message is not really helpful...
Should it be ".padW and .padH are missing"?
from cunn.
did you update cunn to the latest trunk? seems like you updated nn, but not cunn?
from cunn.
https://github.com/torch/cunn/blob/master/SpatialConvolutionMM.cu#L111
from cunn.
Everything is just to the latest release.
OK, tnx for the pointer, but I think there should be a different error message. Don't you think so?
from cunn.
i think that has to be double-checked.
bad argument #1 (field padding does not exist)
This error appears on the older version of cunn for sure, because of this line:
Line 124 in 30e394d
but should not appear in trunk, because it is changed to:
https://github.com/torch/cunn/blob/master/SpatialConvolutionMM.cu#L111
from cunn.
@soumith, my bad. apt-get
broke cuda
and luarocks
didn't update cunn
and I didn't notice that. My fault. Sorry...
from cunn.
no problem :)
from cunn.
👍
from cunn.
@soumith, one more note. With a broken cuda
, luarocks
installed only the lua
files leaving out the cu
one. That's why I had the lua
killing my padding
variable but the precompiled cu
one asking for it. So, the semi-installed cunn
gave me some weird troubles.
from cunn.
Related Issues (20)
- CPU and GPU gave different results HOT 1
- use memory of GPU for a process HOT 3
- Jetson Tx2 compile error HOT 3
- wrong number of arguments for function call with ClassNLLCriterion HOT 5
- Utilizing multiple gpus with different memory to full use
- PReLU tests from test.lua give error
- CUDA fails after installation HOT 1
- Model faster in GeForce GTX 1060 6 GB compared to Google cloud K80 12 GB, missing something?
- THREAD PANIC and Segmentation fault when passing data parallelized model between threads
- Strange issue with DataParallelTable on 1080 Ti HOT 1
- How to implement own c/cuda module in cunn and nn?
- Inconsistence in SpatialMaxPooling and SpatialMaxUnpooling operations for torch.CudaTensor that leads to an error
- error: identifier "WARP_SHFL_XOR" is undefined
- Bug: spatialdepthwiseconvolution has memory leak problem HOT 2
- How to resume training from a certain epoch or how to update an already trained model in torch ?
- /torch/install/share/lua/5.1/cunn/THCUNN.lua:119: table index is nil issue HOT 1
- Fails to build against CUDA9 HOT 1
- CMake Error at THCUNN_generated_LookupTable.cu.o.cmake:267 (message):
- I got this to compile on Ubuntu 20.04 HOT 1
- Problems while Compiling with CUDA11, Ubuntu 20.04 HOT 2
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 cunn.