Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 7 of 7 for 128x512xi8 (0.12 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/experimental/tac/tests/fold-constants-to-subgraph.mlir 

    module {
func.func @main(%arg0: tensor<384x512x!quant.uniform<i8:f32, 0.1>>) -> tensor<384x128x!quant.uniform<i8:f32, 0.09:-4>> {
  %0 = "tfl.pseudo_qconst"() {qtype = tensor<128x512x!quant.uniform<i8<-127:127>:f32, 0.01>>, value = dense<0> : tensor<128x512xi8>} : () -> tensor<128x512x!quant.uniform<i8<-127:127>:f32, 0.01>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 10.5K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/experimental/tac/tests/get-alternative-subgraph.mlir 

    // CHECK:         }
}

// -----

module {
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 20.1K bytes
    - Viewed (0)
  4. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/experimental/tac/tests/compute-cost.mlir 

      func.return %1 : tensor<10x10x10xf32>
}

// -----

// CHECK: tac.cost = 0x4B673001
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Mar 24 05:29:10 UTC 2022
    - 4.1K bytes
    - Viewed (0)
  5. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/tests/quantize_weights.mlir 

    // CHECK-DAG: %[[W:.*]] = "tf.Const"() <{value = dense<127> : tensor<512x512xi8>
// CHECK: %[[PRESERVE_W:.*]] = "tf.Identity"(%[[W]]) : (tensor<512x512xi8>) -> tensor<512x512xi8>
// CHECK: %[[DEQUANTIZED:.*]] = "tf.PartitionedCall"(%[[PRESERVE_W]]) <{config = "", config_proto = "", executor_type = "", f = @composite_dequantize_uniform}> : (tensor<512x512xi8>) -> tensor<512x512xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 42K bytes
    - Viewed (0)
  6. github.com/tensorflow/tensorflow

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

    func.func @RemoveTrival(%arg0: tensor<384x512x!quant.uniform<i8:f32, 1.0:-128>>, %arg1: tensor<128x512x!quant.uniform<i8<-127:127>:f32, 1.0>>, %arg2: none) -> tensor<384x128x!quant.uniform<i8:f32, 2.0>> {
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 19.9K bytes
    - Viewed (0)
  7. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/const-fold.mlir 

      %cst_weights = arith.constant dense<2> : tensor<1024x512xi8>
  %cst_bias = arith.constant dense<4.0> : tensor<1024xf32>

  %0 = "tfl.fully_connected" (%cst_input, %cst_weights, %cst_bias) {fused_activation_function = "NONE", keep_num_dims = false, weights_format = "DEFAULT"} : (tensor<512xf32>, tensor<1024x512xi8>, tensor<1024xf32>) -> tensor<1024xf32>

  func.return %0 : tensor<1024xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 45.8K bytes
    - Viewed (0)
  8. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/optimize.mlir 

      %cst_add = arith.constant dense<2.0> : tensor<512xf32>
  %cst_weights = "tfl.pseudo_qconst"() {qtype = tensor<3072x512x!quant.uniform<i8<-127:127>:f32, 0.039600040763616562>>, value = dense<1> : tensor<1024x512xi8>} : () -> tensor<1024x512x!quant.uniform<i8<-127:127>:f32, 0.039600040763616562>>
  %cst_bias = arith.constant dense<5.0> : tensor<1024xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 16 20:31:41 UTC 2024
    - 284.1K bytes
    - Viewed (0)
Back to top