-
(Feature request)
I want to write a custom image processing function; it would be useful to have a function that allows processing a NxM (e.g. 3x3) sliding window over an image. I ran the below code,…
-
Can someone explain to me the meaning behind the following parameters?
residual_channels": 32,
dilation_channels": 32,
skip_channels": 512,
I could not find a definition for what these paramete…
-
**Describe the bug**
Method mlx.core.conv_general is significantly slower than PyTorch analog. Can vary from 10x to 150x slower.
**To Reproduce**
Just run the attached code.
Include code snipp…
-
I'm curious about how direct convolution is faster than the OpenCL Winograd version.
Do you have an explanation for this difference? You also wrote that there is a bunch of work to do - do you have…
-
Hello!
Gemmini is on branch `dev` and `gemmini-rocc-test` is at 000d2fd.
After passing the CONV (I defined the fast in `conv.c`) test with default configs, I set `hasIm2col = true` in `Configs.sc…
-
http://doras.dcu.ie/22134/1/ios-press-object.pdf
-
@naibaf7 Can you please be kind enough to provide some instructions for installation/training and inference?
1. I have "already" caffe compiled and installed (opencl with Libdnn, ubuntu).
Now do…
-
If I implemented direct conv with ordinary multithreading, what gaps would I have with skimcaffe implementations?
NHZlX updated
7 years ago
-
#### Related to Community Detection
- Large graph visualization using community detection
- Circling a set of nodes with a boundary such that obstruction is proportional to BFS
- [Nearly Balanced…
-
**Is your feature request related to a problem? Please describe.**
Hello! Big thanks for this program and great Getting Started guide. On the main page I found "Note that CUDA accelerated SRGANs/Waif…