Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 3 of 3 for 1x224x224x3xi8 (0.18 sec)

  1. tensorflow/compiler/mlir/quantization/tensorflow/tests/replace_cast_hacks_with_tf_xla_ops_large_constants.mlir

        %1 = "tf.PartitionedCall"(%0, %cst, %cst_0, %cst_1, %cst_4, %cst_5, %cst_2, %cst_3) {config = "", config_proto = "", executor_type = "", f = @quantized_conv2d_with_relu_fn_0} : (tensor<1x2240x2240x3xi8>, tensor<960x960x3x512xi8>, tensor<f32>, tensor<i32>, tensor<512xf32>, tensor<512xi32>, tensor<f32>, tensor<i32>) -> tensor<1x2240x1120x512xi8>...
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 5.9K bytes
    - Viewed (0)
  2. tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir/quantization.mlir

    // CHECK-LABEL: main
    func.func @main(%arg0: tensor<1x224x224x3xf32>) -> tensor<1x401408xf32> {
    // CHECK:   %{{.*}} = "tfl.quantize"(%{{.*}}) <{qtype = tensor<1x224x224x3x!quant.uniform<u8:f32, 7.812500e-03:128>>}> : (tensor<1x224x224x3xf32>) -> tensor<1x224x224x3x!quant.uniform<u8:f32, 7.812500e-03:128>>
    // The float values here doesn't match exactly because double -> float -> double is lossy
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 4.3K bytes
    - Viewed (0)
  3. tensorflow/compiler/mlir/lite/tests/default_quant_params.mlir

    // CHECK: return %[[dq]]
    }
    
    // CHECK-LABEL: test_conv_2d_add
    func.func @test_conv_2d_add(%arg0: tensor<1x224x224x3x!quant.uniform<u8:f32, 1.0>>, %arg1: tensor<32x3x3x3x!quant.uniform<u8<1:255>:f32, 1.0>>, %arg2: tensor<32x!quant.uniform<i32:f32, 1.0>>) -> tensor<1x112x112x32x!quant.uniform<u8:f32, 1.0>> {
        %0 = "tfl.dequantize"(%arg0) : (tensor<1x224x224x3x!quant.uniform<u8:f32, 1.0>>) -> tensor<1x224x224x3xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 8.8K bytes
    - Viewed (0)
Back to top