experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Change ops to raw_ops for linking

Browse Source 
Formatting ops like `raw_ops.Add` will link ops automatically to corresponding documentation.

PiperOrigin-RevId: 305010877
Change-Id: Ia6bda869aed9a3f49f78c11037b3e1ab89bb7289
This commit is contained in:
Taehee Jeong 2020-04-06 06:00:52 -07:00 committed by TensorFlower Gardener
parent 9fbe2a4de4
commit cf88f3c5d2
1 changed files with 16 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
tensorflow/lite/g3doc/performance/coreml_delegate.md
View File

@ -85,30 +85,30 @@ TfLiteCoreMlDelegateDelete(delegate);
Following ops are supported by the Core ML delegate. Following ops are supported by the Core ML delegate.
* `raw_ops.Add` * Add
* Only certain shapes are broadcastable. In Core ML tensor layout, * Only certain shapes are broadcastable. In Core ML tensor layout,
following tensor shapes are broadcastable. `[B, C, H, W]`, `[B, C, 1, following tensor shapes are broadcastable. `[B, C, H, W]`, `[B, C, 1,
1]`, `[B, 1, H, W]`, `[B, 1, 1, 1]`. 1]`, `[B, 1, H, W]`, `[B, 1, 1, 1]`.
* `raw_ops.AveragePool2D` * AveragePool2D
* `raw_ops.Concat` * Concat
* `raw_ops.Conv2D` * Conv2D
* Weights and bias should be constant. * Weights and bias should be constant.
* `raw_ops.DepthwiseConv2D` * DepthwiseConv2D
* Weights and bias should be constant. * Weights and bias should be constant.
* `raw_ops.Hardswish` * Hardswish
* `raw_ops.Logistic` (aka Sigmoid) * Logistic (aka Sigmoid)
* `raw_ops.MaxPool2D` * MaxPool2D
* `raw_ops.Mul` * Mul
* Only certain shapes are broadcastable. In Core ML tensor layout, * Only certain shapes are broadcastable. In Core ML tensor layout,
following tensor shapes are broadcastable. `[B, C, H, W]`, `[B, C, 1, following tensor shapes are broadcastable. `[B, C, H, W]`, `[B, C, 1,
1]`, `[B, 1, H, W]`, `[B, 1, 1, 1]`. 1]`, `[B, 1, H, W]`, `[B, 1, 1, 1]`.
* `raw_ops.Relu` * Relu
* `raw_ops.ReluN1To1` * ReluN1To1
* `raw_ops.Relu6` * Relu6
* `raw_ops.Reshape` * Reshape
* `raw_ops.ResizeBilinear` * ResizeBilinear
* `raw_ops.SoftMax` * SoftMax
* `raw_ops.Tanh` * Tanh
## Feedback ## Feedback