- Sort Score
- Result 10 results
- Languages All
Results 1 - 4 of 4 for 16x8x8x3xf32 (0.14 sec)
-
tensorflow/compiler/mlir/lite/experimental/tac/tests/fold-constants-to-subgraph.mlir
%0 = "tfl.pseudo_const"() {value = dense<1.000000e+00> : tensor<16x3x3x3xf32>} : () -> tensor<16x3x3x3xf32> %1 = "tfl.pseudo_const"() {value = dense<1.000000e+00> : tensor<16xf32>} : () -> tensor<16xf32> %2 = func.call @fold_all_test(%arg0, %0, %1) : (tensor<256x32x32x3xf32>, tensor<16x3x3x3xf32>, tensor<16xf32>) -> tensor<256x30x30x16xf32> func.return %2 : tensor<256x30x30x16xf32> }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 10.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/tests/passes/defer_activation_transpose.mlir
// permutated to match the new input shape. // CHECK: (tensor<1x16x16x4xf32>, tensor<f32>) -> tensor<1x8x8x4xf32> // Check that a `stablehlo.transpose` is added to the result to match the shape // of the users. // CHECK: %[[TRANSPOSE:.+]] = stablehlo.transpose %[[REDUCE_WINDOW]], dims = [0, 3, 1, 2] : (tensor<1x8x8x4xf32>) -> tensor<1x4x8x8xf32> // CHECK: return %[[TRANSPOSE]] // -----
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 18 20:32:46 UTC 2024 - 14.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/prepare-tf-fake-quant.mlir
func.return %rst : tensor<256x8x7x16xf32> // CHECK-DAG: %[[CONSTANT:.*]] = arith.constant dense<0.000000e+00> : tensor<16xf32> // CHECK-DAG: %[[CONSTANT0:.*]] = arith.constant dense<0.000000e+00> : tensor<16x3x3x3xf32> // CHECK: %[[QUANTIZE:.*]] = "tfl.quantize"(%[[CONSTANT0]]) <{qtype = tensor<16x3x3x3x!quant.uniform<u8:f32, 1.000000e+00>>}> // CHECK: %[[DEQUANTIZE:.*]] = "tfl.dequantize"(%[[QUANTIZE]])
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 20.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/prepare-tf-fake-quant-4bit.mlir
func.return %rst : tensor<256x8x7x16xf32> // CHECK-DAG: %[[CONSTANT:.*]] = arith.constant dense<0.000000e+00> : tensor<16xf32> // CHECK-DAG: %[[CONSTANT0:.*]] = arith.constant dense<0.000000e+00> : tensor<16x3x3x3xf32> // CHECK: %[[QUANTIZE:.*]] = "tfl.quantize"(%[[CONSTANT0]]) <{qtype = tensor<16x3x3x3x!quant.uniform<u4:f32, 1.000000e+00>>}> // CHECK: %[[DEQUANTIZE:.*]] = "tfl.dequantize"(%[[QUANTIZE]])
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 22K bytes - Viewed (0)