Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 2 of 2 for 1x256x16xf32 (0.11 sec)

  2. github.com/tensorflow/tensorflow

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

      %1 = "tfl.softmax"(%0) {beta = 1.000000e+00 : f32} : (tensor<1x6x6x16xf32>) -> tensor<1x6x6x16xf32>
  func.return %1 : tensor<1x6x6x16xf32>

// CHECK: %[[sm:.*]] = "tfl.softmax"(%arg0)
// CHECK: %[[dq:.*]] = "tfl.dequantize"(%[[sm]]) : (tensor<1x6x6x16x!quant.uniform<u8:f32, 3.906250e-03>>) -> tensor<1x6x6x16xf32>
// CHECK: return %[[dq]] : tensor<1x6x6x16xf32>
}
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue May 28 23:10:13 UTC 2024
    - 39.7K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

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

      func.return %2 : tensor<4x256x36xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 13.1K bytes
    - Viewed (0)
Back to top