- Sort Score
- Result 10 results
- Languages All
Results 11 - 20 of 40 for RELU (0.05 sec)
-
tensorflow/compiler/mlir/lite/transforms/optimize_patterns.td
(HasRankAtMost<4> $a), (HasRankAtMost<4> $b)]>; } // We can eliminate Relu from Relu(SquaredDifference(x, y)), // since the result of SquaredDifference is always non-negative. // TFLite interpreter doesn't support Relu+int32 for now. So the test cases // are failing without the following pattern to optimize Relu away fixes // the problem. def OptimizeReluSquaredDifference : Pat<
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 16 20:31:41 UTC 2024 - 66.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/tfl_while_outline.mlir
%14 = "tfl.relu"(%10#1) : (tensor<4x2xf32>) -> tensor<4x2xf32> %15 = "tfl.logistic"(%10#0) : (tensor<4x2xf32>) -> tensor<4x2xf32> %16 = tfl.mul %15, %14 {fused_activation_function = "NONE"} : tensor<4x2xf32> %17 = tfl.add %13, %16 {fused_activation_function = "NONE"} : tensor<4x2xf32> %18 = "tfl.relu"(%17) : (tensor<4x2xf32>) -> tensor<4x2xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 13.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/passes/merge_fusion_with_dequantize.cc
func_op.eraseResult(0); func_op.insertResult(0, new_call_op.getResult(0).getType(), /*resultAttrs=*/nullptr); // Modify the quantized fused function to do dequantize+relu(6). rewriter.setInsertionPoint(req_op); Value new_result = rewriter.create<mlir::stablehlo::UniformDequantizeOp>( req_op.getLoc(), func_op.getResultTypes()[0], req_op.getOperand());
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 5.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/tfrt/tests/tf_to_corert/tf_to_corert_pipeline.mlir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 08 00:18:59 UTC 2024 - 7.7K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/prepare-quantize-dynamic-range.mlir
%broad2_s = "quantfork.stats"(%broad2) {layerStats = dense<[0.000000e+00, 1.000000e+01]> : tensor<2xf32>} : (tensor<?x26x26x26x16xf32>) -> tensor<?x26x26x26x16xf32> %add = "tfl.add"(%broad1_s, %broad2_s) {fused_activation_function = "RELU"} : (tensor<?x26x26x26x16xf32>, tensor<?x26x26x26x16xf32>) -> tensor<?x26x26x26x16xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 38.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/transforms/legalize_patterns.td
(TFL_RangeOp $start, $limit, $delta)>; def LegalizeRelu6 : Pat<(TF_Relu6Op $arg), (TFL_Relu6Op $arg)>; def LegalizeRelu : Pat<(TF_ReluOp $arg), (TFL_ReluOp $arg)>; // TFL Relu doesn't support I32/I64 type, so legalizes TF Relu to TFL Maximum. def LegalizeReluI32 : Pat<(TF_ReluOp TensorOf<[I32]>:$arg), (TFL_MaximumOp $arg, (Arith_ConstantOp ConstantAttr<RankedI32ElementsAttr<[]>,"0">))>;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 04 13:30:42 UTC 2024 - 28.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/tests/pipelines/process_nchw_tensor.mlir
%0 = stablehlo.constant dense<2.000000e+00> : tensor<4x2x3x3xf32> // weight %1 = stablehlo.constant dense<3.000000e+00> : tensor<4xf32> // bias %2 = stablehlo.constant dense<0.000000e+00> : tensor<1x4x5x5xf32> // relu %3 = stablehlo.broadcast_in_dim %1, dims = [1] : (tensor<4xf32>) -> tensor<1x4x5x5xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 18 20:32:46 UTC 2024 - 12.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/schema/schema_v3b.fbs
HASHTABLE_LOOKUP = 10, L2_NORMALIZATION = 11, L2_POOL_2D = 12, LOCAL_RESPONSE_NORMALIZATION = 13, LOGISTIC = 14, LSH_PROJECTION = 15, LSTM = 16, MAX_POOL_2D = 17, MUL = 18, RELU = 19, // NOTE(aselle): RELU_N1_TO_1 used to be called RELU1, but it was renamed // since different model developers use RELU1 in different ways. Never // create another op called RELU1. RELU_N1_TO_1 = 20,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 28 14:28:27 UTC 2024 - 30K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/quantize-numeric-verify.mlir
%2 = "tfl.pseudo_const"() {value = dense<0.000000e+00> : tensor<3xf32>} : () -> tensor<3xf32> %3 = "tfl.conv_2d"(%0, %1, %2) { dilation_h_factor = 1 : i32, dilation_w_factor = 1 : i32, fused_activation_function = "RELU", padding = "VALID", stride_h = 1 : i32, stride_w = 1 : i32} : ( tensor<?x5x5x2xf32>, tensor<3x5x5x2xf32>, tensor<3xf32>) -> tensor<?x1x1x3xf32> %4 = "quantfork.stats"(%3) {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 15.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/tests/passes/lift_quantizable_spots_as_functions.mlir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 10 04:07:09 UTC 2024 - 49.8K bytes - Viewed (0)