Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 9 of 9 for 2x3x3x2xi8 (0.17 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/tf2xla/tests/legalize-tf-quant.mlir 

      %weight_scales = "tf.Const"() { value = dense<1.0> : tensor<f32> } : () -> tensor<f32>
  %weight_zps = "tf.Const"() { value = dense<3> : tensor<i32> } : () -> tensor<i32>

  // CHECK: %[[CONST:.*]] = mhlo.constant()
  // CHECK-SAME{LITERAL} value = dense<127> : tensor<2x3x3x2xi8>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 09 01:25:29 UTC 2024
    - 37.3K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/stablehlo/tests/compose-uniform-quantized-type.mlir 

        %0 = stablehlo.convert %arg0 : (tensor<1x3x3x4xf32>) -> tensor<1x3x3x4xi8>
    return %0 : tensor<1x3x3x4xi8>
  }
// CHECK: @uniform_quantize_1
  func.func private @uniform_dequantize_0(%arg0: tensor<1x3x3x4xi8>, %arg1: tensor<1x1x1x1xf32>, %arg2: tensor<1x1x1x1xi8>) -> tensor<1x3x3x4xf32> {
    %0 = stablehlo.convert %arg0 : (tensor<1x3x3x4xi8>) -> tensor<1x3x3x4xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue May 14 17:10:32 UTC 2024
    - 37K bytes
    - Viewed (0)
  4. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/modify_io_nodes.mlir 

      %1 = "tfl.pseudo_qconst"() {qtype = tensor<32x3x3x3x!quant.uniform<i8<-127:127>:f32, 0.021826678373682216:151>>, value = dense<-76> : tensor<32x3x3x3xi8>} : () -> tensor<32x3x3x3x!quant.uniform<i8<-127:127>:f32, 0.021826678373682216>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 19.9K bytes
    - Viewed (0)
  5. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/tests/quantize_xla.mlir 

      %q_weight = "quantfork.qcast"(%weight) : (tensor<2x3x3x2xf32>) -> tensor<2x3x3x2x!quant.uniform<i8:f32, 0.074855112561992565:-1>>
  %dq_weight = "quantfork.dcast"(%q_weight) : (tensor<2x3x3x2x!quant.uniform<i8:f32, 0.074855112561992565:-1>>) -> tensor<2x3x3x2xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed May 08 19:32:28 UTC 2024
    - 11.4K bytes
    - Viewed (0)
  6. github.com/tensorflow/tensorflow

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

    // CHECK: %[[Q:.+]] = "quantfork.qcast"(%[[CST]]) : (tensor<2x3x3x2xf32>) -> tensor<2x3x3x2x!quant.uniform<i8<-127:127>:f32, 0.0023622048182750312>>
// CHECK: %[[DQ:.+]] = "quantfork.dcast"(%[[Q]]) : (tensor<2x3x3x2x!quant.uniform<i8<-127:127>:f32, 0.0023622048182750312>>) -> tensor<2x3x3x2xf32>
// CHECK: %[[CALL:.+]] = "tf.XlaCallModule"(%[[ARG_0]], %[[DQ]])
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 09 05:56:10 UTC 2024
    - 22K bytes
    - Viewed (0)
  7. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/decompose-hybrid-quantization.mlir 

    func.func @test_depthwise_conv2d_replace_float(%arg0: tensor<1x224x224x3xf32>) -> tensor<1x112x112x32xf32> {
  // CHECK-DAG: %[[VAL0:.+]] = "tfl.pseudo_qconst"() <{qtype = tensor<32x3x3x3x!quant.uniform<{{.+}}>>, value = dense<42> : tensor<32x3x3x3xi8>}>
  // CHECK-DAG: %[[VAL1:.+]] = "tfl.pseudo_qconst"() <{qtype = tensor<32x!quant.uniform<{{.+}}>>, value = dense<0> : tensor<32xi32>}>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 13.1K bytes
    - Viewed (0)
  8. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/post-quantize.mlir 

      %1 = "tfl.pseudo_qconst"() {qtype = tensor<32x3x3x3x!quant.uniform<u8<1:255>:f32, 0.021826678373682216:151>>, value = dense<-76> : tensor<32x3x3x3xi8>} : () -> tensor<32x3x3x3x!quant.uniform<u8<1:255>:f32, 0.021826678373682216:151>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 19.9K bytes
    - Viewed (0)
  9. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/quantize.mlir 

    // CHECK: %[[cst1:.*]] = "tfl.pseudo_qconst"() <{qtype = tensor<32x3x3x3x!quant.uniform<u8<1:255>:f32, 1.000000e-01>>, value = dense<1> : tensor<32x3x3x3xi8>}>
// CHECK: %[[conv:.*]] = "tfl.conv_2d"(%arg0, %[[cst1]], %[[cst0]])
// CHECK: return %[[conv]] : tensor<1x112x112x32x!quant.uniform<u8:f32, 0.023528476789885875>>
}

// CHECK-LABEL: QuantizeConv2D4Bit
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue May 28 23:10:13 UTC 2024
    - 39.7K bytes
    - Viewed (0)
  10. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/quantize-numeric-verify.mlir 

      %3 = "tfl.pseudo_qconst"() {qtype = tensor<32x3x3x3x!quant.uniform<u8<1:255>:f32, 0.021826678373682216:151>>, value = dense<-76> : tensor<32x3x3x3xi8>} : () -> tensor<32x3x3x3x!quant.uniform<u8<1:255>:f32, 0.021826678373682216:151>>
  %4 = "tfl.dequantize"(%3) : (tensor<32x3x3x3x!quant.uniform<u8<1:255>:f32, 0.021826678373682216:151>>) -> tensor<32x3x3x3xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 15.1K bytes
    - Viewed (0)
Back to top