Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 3 of 3 for tfl_quantizer (0.18 sec)

  1. tensorflow/compiler/mlir/lite/quantization/lite/tfl_quantizer.cc

    A. Unique TensorFlower <******@****.***> 1718231025 -0700
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed Jun 12 23:15:24 UTC 2024
    - 2.4K bytes
    - Viewed (0)
  2. tensorflow/compiler/mlir/lite/quantization/lite/BUILD

            "@llvm-project//mlir:QuantOps",
            "@llvm-project//mlir:Support",
        ],
    )
    
    # Binary to apply quantization on the annotated files.
    tf_cc_binary(
        name = "tfl_quantizer",
        srcs = [
            "tfl_quantizer.cc",
        ],
        deps = [
            ":quantize_model",
            "//tensorflow/compiler/mlir/lite/schema:schema_fbs",
            "//tensorflow/lite:framework",
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed Jun 12 23:15:24 UTC 2024
    - 8.3K bytes
    - Viewed (0)
  3. tensorflow/compiler/mlir/lite/transforms/quantize_patterns.td

    // squashed to a requantize op if the scales are different.
    def : Pat<(TFL_QuantizeOp (TFL_DequantizeOp $in), $qt), (replaceWithValue $in)>;
    
    // If the tfl.dequantize op wasn't fused, we shouldn't quantize the floating
    // point constant.
    def : Pat<(TFL_DequantizeOp
                 (TFL_QuantizeOp (Arith_ConstantOp F32ElementsAttr:$cst), $qt)),
              (TFL_ConstOp $cst)>;
    
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue May 28 23:10:13 UTC 2024
    - 2.3K bytes
    - Viewed (0)
Back to top