Skip to content

Commit

Permalink
Remove optimize lq.quantize(tfl.dequantize(x)) in more cases
Browse files Browse the repository at this point in the history
  • Loading branch information
lgeiger committed Apr 8, 2022
1 parent 37f05c9 commit 922a701
Showing 1 changed file with 3 additions and 0 deletions.
3 changes: 3 additions & 0 deletions larq_compute_engine/mlir/tf_tfl_passes.cc
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,9 @@ void AddQuantizationPasses(const mlir::TFL::QuantizationSpecs& quant_specs,
quant_specs.inference_type != quant_specs.inference_input_type;
pass_manager->addNestedPass<mlir::FuncOp>(
mlir::TFL::CreatePostQuantizePass(emit_quant_adaptor_ops));
pass_manager->addPass(mlir::TFL::CreateLCEQuantizePass());
pass_manager->addNestedPass<mlir::FuncOp>(
mlir::TFL::CreatePostQuantizePass(emit_quant_adaptor_ops));
}
} // namespace

Expand Down

0 comments on commit 922a701

Please sign in to comment.