Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 2 of 2 for 4x128xf32 (0.09 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/optimize_batch_matmul.mlir 

      func.return %1 : tensor<4x128x1xf32>

  // CHECK: %[[TRANSPOSED_X:.*]] = "tfl.transpose"
  // CHECK-SAME: (tensor<4x2x128xf32>, tensor<3xi32>) -> tensor<4x128x2xf32>
  // CHECK-NEXT: %[[FC_RES:.*]] = "tfl.fully_connected"(%[[TRANSPOSED_X]]
  // CHECK-SAME: <{fused_activation_function = "NONE", keep_num_dims = true, weights_format = "DEFAULT"}> : (tensor<4x128x2xf32>, tensor<1x2xf32>, none) -> tensor<4x128x1xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 9K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/stablehlo/tests/legalize-tfl-stablehlo-pad.mlir 

    module {
    func.func @main(%arg0: tensor<8x128xf32>, %arg1: tensor<f32>) -> tensor<11x131xf32> {
      %0 = "tfl.custom"(%arg0, %arg1) {custom_code = "stablehlo.pad", custom_option = #tfl<const_bytes : "0x656467655F70616464696E675F6869676800020203656467655F70616464696E675F6C6F7700020100696E746572696F725F70616464696E6700020000033E2A17030103311E0B2C2C2C062401">} : (tensor<8x128xf32>, tensor<f32>) -> tensor<11x131xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Dec 11 20:41:19 UTC 2023
    - 939 bytes
    - Viewed (0)
Back to top