Wanming Lin
cd516a1677
[WebNN EP] Remove constraint for conv ops on CPU backend ( #21237 )
...
Currently WebNN TFLite backend allows the filter of
conv2d/convTranspose2d be an input. Remove the constraint and operate
necessary transpose/reshape operations for the filter input.
2024-07-08 10:14:43 -07:00
Wanming Lin
41ad83fb00
[WebNN EP] Support rest Reduction ops for TFLite backend ( #21135 )
...
- reduceLogSum, reduceLogSumExp and reduceSumSquare have been landed in
https://chromium-review.googlesource.com/c/chromium/src/+/5575815
- reduceL1 and reduceL2 have been landed in
https://chromium-review.googlesource.com/c/chromium/src/+/5606091
2024-06-25 18:30:55 -07:00
Wanming Lin
4743803944
[WebNN EP] Support more Normalization ops for TFLite backend ( #21151 )
...
Following Normalization ops have been supported in Chromium for TFLite
backend:
- batchNormalization:
https://chromium-review.googlesource.com/c/chromium/src/+/5532745
- layerNormalization:
https://chromium-review.googlesource.com/c/chromium/src/+/5573326
- instanceNormalization:
https://chromium-review.googlesource.com/c/chromium/src/+/5532750
2024-06-24 19:04:23 -07:00
Wanming Lin
3a917e49fb
[WebNN EP] Support 4 more ops for TFLite backend ( #21134 )
...
Recently WebNN TFLite backend supports gelu, expand, softsign,
reciprocal.
2024-06-24 09:52:12 -07:00
Wanming Lin
0c80cd2157
[WebNN EP] Update Prelu restriction for CPU backend ( #20878 )
2024-06-20 11:04:01 -07:00
Wanming Lin
40879a2623
[WebNN EP] Enable Cast op for WebNN CPU backend ( #20864 )
...
WebNN TFLite backend supports `cast` op but doesn't support casting to
`uint64` data type.
2024-06-19 01:51:19 -07:00
Wanming Lin
35c430a95a
[WebNN EP] Enable several ops for WebNN CPU backend ( #20847 )
...
WebNN CPU implementation has been migrated from XNNPack to TFLite which
supports more ops. Turn on partial `cpu` supported ops which just need
the change from `false` to `true` firstly.
2024-06-19 01:45:31 -07:00
Wanming Lin
043ef5c95f
[WebNN EP] Support latest WebNN softmax op ( #20827 )
...
Latest WebNN softmax supports N-D input and axis parameter.
2024-06-11 08:27:14 -07:00
Wanming Lin
52874f628a
[WebNN EP] Remove some constraints for CPU backend ( #20900 )
...
Following constraints have been supported by WebNN TFLite backend:
- Concat: supports up to 4 inputs
- Matmul: supports broadcasting
- Resize: supports nearest mode
- Split: supports up to 4 outputs
2024-06-06 08:22:41 -07:00
Wanming Lin
da1f8f9274
[WebNN EP] TFLite backend only supports limit ranges for Clip ( #20863 )
2024-06-06 08:22:18 -07:00
Wanming Lin
9c6481fa2d
[WebNN EP] Enable ArgMax and ArgMin for CPU backend ( #20865 )
...
WebNN TFLite backend supports ArgMax and ArgMin, but only supports
'select_last_index' value is 0.
2024-06-03 14:12:11 -07:00
Wanming Lin
c128132dd8
[WebNN EP] TFLite backend only supports Elu with default alpha ( #20862 )
2024-06-03 14:10:22 -07:00
Peishen Yan
cfe68e489e
[WebNN EP] Support Trilu op ( #20730 )
...
Adds support for Trilu via WebNN Triangular op
2024-05-24 10:46:54 -07:00
Wanming Lin
2c39d0c502
[WebNN EP] Disable ConvTranspose for WebNN CPU ( #20762 )
...
WebNN CPU backend implementation has been migrated from XNNPack to
TFLite, currently TFLite has not supported WebNN's convTranspose2d yet,
just disable it for now.
2024-05-22 20:59:37 -07:00
Wanming Lin
da86f6f408
[WebNN EP] Add operators support table ( #20253 )
2024-04-17 21:19:46 -07:00
