- Sort Score
- Result 10 results
- Languages All
Results 1 - 1 of 1 for QuantizePass (0.14 sec)
-
tensorflow/compiler/mlir/lite/transforms/prepare_tf.cc
ConvertTFDilatedConvOp<TF::DepthwiseConv2dNativeOp>>(ctx); patterns.add<RemoveIdentity>(ctx); TFL::populateWithGenerated(patterns); // TODO(fengliuai): Implement similar rule in the QuantizePass if the constant // folding hook of tfl.transpose and tfl.reshape are implemented. patterns.add<ReorderFakeQuantPattern<TF::ReshapeOp>, ReorderFakeQuantPattern<TF::TransposeOp>>(ctx);
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 28 21:49:50 UTC 2024 - 64.6K bytes - Viewed (0)