Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 4 of 4 for 1x3x4x3xi8 (0.15 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/tests/replace_cast_hacks_with_tf_xla_ops.mlir 

        %2 = "tf.Cast"(%1) : (tensor<1x3x4x3xf32>) -> tensor<1x3x4x3xi32>
    %3 = "tf.AddV2"(%2, %arg2) : (tensor<1x3x4x3xi32>, tensor<i32>) -> tensor<1x3x4x3xi32>
    %4 = "tf.Cast"(%3) {Truncate = false} : (tensor<1x3x4x3xi32>) -> tensor<1x3x4x3xi8>
    return %4 : tensor<1x3x4x3xi8>
  }
  func.func private @dequantize_i8(%arg0: tensor<1x3x2x2xi8>, %arg1: tensor<f32>, %arg2: tensor<i32>) -> tensor<1x3x2x2xf32> {
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 81K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/stablehlo/tests/passes/quantize_composite_functions.mlir 

    // CHECK: %[[CALL_0:.+]] = call @quantized_conv_fn(%[[UNIFORM_QUANTIZE_0]], %[[CONST_0]])
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 09 05:56:10 UTC 2024
    - 91.6K bytes
    - Viewed (0)
  4. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/experimental/tac/tests/raise-target-subgraphs.mlir 

      %0 = "tfl.pseudo_qconst"() {qtype = tensor<1x384x1x!quant.uniform<i8:f32, 0.003:-128>>, value = dense<127> : tensor<1x384x1xi8>} : () -> tensor<1x384x1x!quant.uniform<i8:f32, 0.003:-128>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 74.9K bytes
    - Viewed (0)
  5. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/tensorflow/tests/lower_tf.mlir 

        // CHECK-DAG:  %[[ONE:.*]] = "tf.Const"() <{value = dense<1.000000e+00> : tensor<f32>}> : () -> tensor<f32>
    // CHECK:   %[[PRED:.*]] = "tf.Greater"(%[[FEATURES]], %[[ZERO]]) : (tensor<1x4x4x3xf32>, tensor<f32>) -> tensor<1x4x4x3xi1>
    // CHECK-NEXT:  %[[SCALED_FEATURES:.*]] = "tf.Mul"(%[[FEATURES]], %[[SCALE]]) : (tensor<1x4x4x3xf32>, tensor<f32>) -> tensor<1x4x4x3xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Fri Jan 05 18:35:42 UTC 2024
    - 92K bytes
    - Viewed (0)
Back to top