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

Fix resize_bilinear type propagation

Browse Source 
This operator supports more than just float32 outputs.

PiperOrigin-RevId: 259411764
This commit is contained in:
Jared Duke 2019-07-22 14:51:30 -07:00 committed by TensorFlower Gardener
parent 98f6e0e82b
commit a9429e942a
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tensorflow/lite/toco/graph_transformations/propagate_array_data_types.cc
View File

@ -55,7 +55,6 @@ void SetDataTypeForAllOutputs(Model* model, Operator* op,
// Do the actual output data types propagation. // Do the actual output data types propagation.
switch (op->type) { switch (op->type) {
case OperatorType::kDequantize: case OperatorType::kDequantize:
case OperatorType::kResizeBilinear:
// These operators unconditionally produce float outputs // These operators unconditionally produce float outputs
SetDataTypeForAllOutputs(model, op, ArrayDataType::kFloat); SetDataTypeForAllOutputs(model, op, ArrayDataType::kFloat);
break; break;