Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 1 of 1 for QuantizedOp1 (0.1 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/passes/prepare_quantize.cc 

    // %1 = tf.QuantizeCastOp(%0) : f32 -> qtype1
// %2 = tf.QuantizeCastOp(%1) : qtype1 -> qtype2
// %3 = tf.QuantizedOp1(%1)
// %4 = tf.QuantizedOp2(%2)
// will be tranformed to:
// %1 = tf.QuantizeCastOp(%0) : f32 -> qtype1
// %2 = tf.QuantizeCastOp(%0) : f32 -> qtype2
// %3 = tf.QuantizedOp1(%1)
// %4 = tf.QuantizedOp2(%2)
// Converting from f32 -> qtype1 -> qtype2 will add unexpected quantization
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 25 16:01:03 UTC 2024
    - 17.2K bytes
    - Viewed (0)
Back to top