Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 2 of 2 for 2x3x3x1024xi8 (0.16 sec)

  2. github.com/tensorflow/tensorflow

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

    // CHECK: %[[IDENTITY_1:.*]] = "tf.Identity"(%[[W_1]]) : (tensor<2x3x3x1024xi8>) -> tensor<2x3x3x1024xi8>
// CHECK: %[[DEQUANTIZED_1:.*]] = "tf.PartitionedCall"(%[[IDENTITY_1]]) <{config = "", config_proto = "", executor_type = "", f = @composite_dequantize_uniform__}> : (tensor<2x3x3x1024xi8>) -> tensor<2x3x3x1024xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 42K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

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

    // CHECK: %[[CAST:.*]] = "tf.Cast"
// CHECK: %[[BROADCAST_TO:.*]] = "tf.BroadcastTo"(%[[CAST]], %[[CONST]]) : (tensor<2x1x1024xi8>, tensor<4xi64>) -> tensor<2x2x1x1024xi8>
// CHECK: %[[XLADOTV2_0:.*]] = "tf.XlaDotV2"(%[[BROADCAST_TO]], %[[WEIGHT]])
}

// -----

module attributes {tf_saved_model.semantics} {
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 81K bytes
    - Viewed (0)
Back to top