Comments (6)
Hi,
Could you be more specific, please?
What configuration is causing the problem?
Or have you found an obvious bug in the source code?
Thank you a lot, we enormously appreciate your feedback.
Best regards,
MIOpen team.
from miopen.
Hi!
I meant that in cuDNN LRN is calculated like:
y_ij = |x_ij| / (K + alpha * (sum_kl x_kl^2) / N^2)^beta
and in MIOpen:
y_ij = x_ij / (K + alpha * (sum_kl x_kl^2) / N^2)^beta
(without abs value of x_ij)
So, may be it should be changed, so in deep learning frameworks LRN layers for NVIDIA and AMD would be similar?
from miopen.
Here is, roughly, the cuda code:
template
global void LRNComputeOutput(const int nthreads, const Dtype* const in,
const Dtype* const scale, const Dtype negative_beta, Dtype* const out) {
CUDA_KERNEL_LOOP(index, nthreads) {
out[index] = in[index] * pow(scale[index], negative_beta);
}
}
X is in[index]
Y is out[index]
Iām not sure where is the difference?
I do not see any abs function here.
Abs will indeed cause the sign loss but LRN is a scaling operation it should keep sign unchanged.
Best regards,
MIOpen team.
from miopen.
Sorry, I meant that in cuDNN it is without abs.
If you look at MIOpen LRN line 385, there is bot_val * s. And bot_val (line 381) is sqrt of something. Therefore, it is always >= 0, we lost a sign.
from miopen.
you're right. some minor optimization can cause a lot of havoc :)
thank you, great catch. we've fixed it already and put it into the next release.
Best regards,
MIOpen team.
from miopen.
@ashmanov this issue has been fixed in the latest release.
from miopen.
Related Issues (20)
- SetTensorNd truncates tensor length for larger lens values in tensor_driver.hpp
- MIOpen for MI300 machine. HOT 9
- MLIR kernel perf regression after #2722 HOT 7
- [conv][fp16][bf16] Gemm solvers fail with big tensors HOT 1
- [conv][fp32] GemmWrWUniversal solver with big tensors fails validation in the driver but passes validation in tests HOT 1
- Implement serialization of tensor descriptors and use it in primitives. HOT 1
- [softmax] Store full info about unpacked tensors in the problem descriptor HOT 3
- Find takes >1 sec for some conv configs HOT 3
- Reordering dimensions using miopenTransformTensor is broken HOT 3
- [MHA] Implement MIOPEN_BACKEND_VARIANT_PACK_DESCRIPTOR in Graph API
- [MHA] Implement point-wise operation descriptor in Graph API HOT 2
- [MHA] Implement batch matrix multiplication descriptor in Graph API
- [MHA] Implement reduction descriptor in Graph API HOT 1
- [MHA] Implement random number generator descriptor in Graph API HOT 2
- [MHA] Implement MIOPEN_BACKEND_OPERATIONGRAPH_DESCRIPTOR in Graph API
- [MHA] Implement MIOPEN_BACKEND_ENGINE_DESCRIPTOR in Graph API
- [MHA] Implement MIOPEN_BACKEND_ENGINECFG_DESCRIPTOR in Graph API
- [MHA] Implement MIOPEN_BACKEND_EXECUTION_PLAN_DESCRIPTOR in Graph API
- Is multiple rank:multiple GPU supported? HOT 1
- "-mno-xnack" flag is removed by upstream clang HOT 6
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
š 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. ššš
-
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 ā¤ļø Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from miopen.