huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-17 02:58:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add some group parameter to convolutions. (#566)

Browse Source 
* Add some group parameter to convolutions.

* Avoid some unnecessary groups checks.

* Move the tensor convolution bits.

* Properh handling of groups.

* Bump the crate version.

* And add a changelog.
This commit is contained in:
Laurent Mazare
2023-08-23 12:58:55 +01:00
committed by GitHub
parent 4ee1cf038a
commit aba1e90797
30 changed files with 216 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
candle-core/examples/basics.rs
View File

@ -11,7 +11,7 @@ fn main() -> Result<()> {
let inp = Tensor::randn(0f32, 1., (2, 320, 96, 96), &Device::Cpu)?;
let w = Tensor::randn(0f32, 1., (320, 320, 3, 3), &Device::Cpu)?;
let start = std::time::Instant::now();
let res = inp.conv2d(&w, 0, 1);
let res = inp.conv2d(&w, 0, 1, 1)?;
println!("{:?}", start.elapsed());
println!("{res:?}");
Ok(())

4
candle-core/examples/cpu_benchmarks.rs
View File

@ -40,7 +40,7 @@ impl Benchmark for Conv1d {
}
fn run_one(d: &Self::PreProcessData) -> Result<Self::RunResult> {
d.0.conv1d(&d.1, 0, 1)
d.0.conv1d(&d.1, 0, 1, 1)
}
const ITERS: usize = 5;
@ -59,7 +59,7 @@ impl Benchmark for Conv2d {
}
fn run_one(d: &Self::PreProcessData) -> Result<Self::RunResult> {
d.0.conv2d(&d.1, 0, 1)
d.0.conv2d(&d.1, 0, 1, 1)
}
const ITERS: usize = 1;

2
candle-core/examples/cuda_basics.rs
View File

@ -11,7 +11,7 @@ fn main() -> Result<()> {
let device = Device::new_cuda(0)?;
let t = Tensor::randn(0f32, 1f32, (2, 4, 96, 96), &device)?;
let w = Tensor::randn(0f32, 1f32, (320, 4, 3, 3), &device)?;
let res = t.conv2d(&w, 1, 1)?;
let res = t.conv2d(&w, 1, 1, 1)?;
println!("{res:?}");
Ok(())
}