mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-28 22:56:32 +00:00
307ad1413a
**Description**:
1. add pytorch_half_pixel interpolation mode in resize-packed.ts
Changes: add the following case in createPackedResizeProgramInfo
function:
```
case 'pytorch_half_pixel':
getSourceFracIndex = `
vec4 getSourceFracIndex(ivec4 coords) {
vec4 fcoords = vec4(coords);
return vec4(
${outputWidth}.0 > 1.0 ? (fcoords.x + 0.5) / scaleWHWH.x - 0.5 : 0.0,
${outputHeight}.0 > 1.0 ? (fcoords.y + 0.5) / scaleWHWH.y - 0.5 : 0.0,
${outputWidth}.0 > 1.0 ? (fcoords.z + 0.5) / scaleWHWH.z - 0.5 : 0.0,
${outputHeight}.0 > 1.0 ? (fcoords.w + 0.5) / scaleWHWH.w - 0.5 : 0.0
);
}
`;
break;
```
2. fix "unrecognized input '' for node: Resize_$num" error when inputs
like [input_tensor, None, scale_factor] (roiInput not given) are fed
into the resize layer.
Changes: change in input handling logic in upsample.ts & node scanning
logic in graph.ts
**Motivation and Context**
Before this fix, we aren't able to use webGL backend when the neural
network contains pytorch resize layers. This fix adds
'pytorch_half_pixel' interpolation mode support and makes it possible to
use webGL backend for more kind of computer vision networks.
This commit solves:
#10430
Co-authored-by: neo <neo@icode-lab.com>
Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com>
|
||
|---|---|---|
| .. | ||
| batch-normalization.ts | ||
| binary-op.ts | ||
| cast.ts | ||
| concat-packed.ts | ||
| concat.ts | ||
| conv-grouped.ts | ||
| conv-pack.ts | ||
| conv-transpose.ts | ||
| conv.ts | ||
| depth-to-space.ts | ||
| dot-product.ts | ||
| flatten.ts | ||
| fuse-utils.ts | ||
| gather.ts | ||
| gemm.ts | ||
| im2col-pack.ts | ||
| im2col.ts | ||
| image-scaler.ts | ||
| instance-normalization.ts | ||
| matmul-pack.ts | ||
| matmul.ts | ||
| pack.ts | ||
| packing-utils.ts | ||
| pad.ts | ||
| pool.ts | ||
| reduce.ts | ||
| reshape-packed.ts | ||
| reshape.ts | ||
| resize-packed.ts | ||
| shape.ts | ||
| slice.ts | ||
| softmax.ts | ||
| split.ts | ||
| squeeze.ts | ||
| sum.ts | ||
| tile.ts | ||
| transpose.ts | ||
| uint8-encode.ts | ||
| unary-op.ts | ||
| unpack.ts | ||
| unsqueeze.ts | ||
| upsample.ts | ||